PAWS Lab - User contributions [en]

People

2019-03-01T18:46:41Z

Jbarriapineda: Go back to have square on the photos

== Faculty ==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
</gallery>

== Doctoral Students ==
<gallery perrow="4">
Image:Tsai.jpg|[http://www.cht77.com/ Chun-Hua Tsai]
Image:Avatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Kamil.jpg|[http://pitt.edu/~kaa108 Kamil Akhuseyinoglu]
Image:zrisha.png|[https://zakrisha.com Zak Risha]
Image:behnam.jpg|[http://pitt.edu/~ber58 Behnam Rahdari]
Image:k.thaker.png|[http://pitt.edu/~kmt81 Khushboo Thaker]
</gallery>

== Visiting Scholars ==
<gallery perrow="4">

</gallery>

== Past Doctoral Students ==
<gallery perrow="4">
Image:Roya.jpg|[[User:R.hosseini | Roya Hosseini]]
Image:yunhuang.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:Julio.jpg|[[User:Julio | Julio Guerra]]
Image:xidao.jpg|[[User:Xidao| Xidao Wen]]
Image:Shaghayeghsahebi.jpg|[[User:Sherry | Shaghayegh Sahebi (Sherry)]] Currently Assistant Professor in the Computer Science Department at State University of New York (SUNY) at Albany
Image:Clau.JPG|[[User:Clau | Claudia López]] Currently Assistant Professor in the Departamento de Informática, Universidad Técnica Federico Santa María, Chile
Image:Kong.png|[[User:Chirayu | Chirayu Wongchokprasitti]] Currently at the Department of Biomedical Informatics, University of Pittsburgh
Image:jennifer.jpg|[[User:Jennifer | Jennifer (Yiling) Lin]] Currently Assistant Professor in the department of Information Management at the National Sun Yat-Sen University.
Image:Denis_PAWS_blog.jpg|[[User:Dparra | Denis Parra]] Currently Assistant Professor at the Computer Science Department, School of Engineering at PUC Chile.
Image:jaewook-1.jpg|[[User:Jahn | Jae-wook Ahn]] Projects: [[ADVISE]], [[Adaptive VIBE]], [[YourNews]], [[YourSports]], [[TaskSieve]], [[NameSieve]] Research Staff Member, Cognitive Sciences and Education,IBM Research
Image:RostaFarzan.jpg|[[User:Rostaf | Rosta Farzan]] Currently Assistant Professor at School of Computing and Information, University of Pittsburgh.
Image:Michael_V_Yudelson.gif|'''[[User:Myudelson | Michael V. Yudelson]]''' Projects: [[Knowledge Tree]], [[CUMULATE]], [[PERSEUS]], [[NavEx]], [[CoPE]], [[WebEx]] Currently Postdoctoral Fellow at Carnegie Mellon University
Image:Sergey.jpg|[[User:Sergey | Sergey Sosnovsky]] Currently Assistant Professor at Utrecht University (the Netherlands)
Image:Hsiao.jpg|[[User:Shoha99 | Sharon (I-Han) Hsiao]] Projects: [[AnnotEx]], [[QuizJET]], [[Progressor]], [[ProgressorPlus]] Currently Assistant Professor @ CIDSE, Arizona State University
Image:Danielle.gif|[[User:Suleehs | Danielle H. Lee]] Projects: [[Eventur]], [[Proactive]] Currently Assistant Professor at the Department of Software, Sangmyung University, Korea
</gallery>

== Past Visiting Faculty ==
<gallery perrow="4">
Image:Susan_bull.png|[https://www.researchgate.net/profile/Susan_Bull2 Susan Bull]
Image:Jaakko peltonen 215x296.jpg|[http://users.ics.aalto.fi/jtpelto// Jaakko Peltonen]
Image:IMG_0611.JPG|[http://www.dcs.warwick.ac.uk/~acristea/ Alexandra I. Cristea]
Image:Sibel.jpg|[http://sibelsomyurek.com/ Sibel Somyürek]
Image:KatrienVerbert.jpg|[http://people.cs.kuleuven.be/~katrien.verbert/KatrienVerbert/Katrien_Verbert.html Katrien Verbert]
Image:Roman bednarik.png|[http://cs.uef.fi/~rbednari/ Roman Bednarik]
Image:TanjaMitrovic.jpg|[http://www.cosc.canterbury.ac.nz/tanja.mitrovic/ Tanja Mitrovic]
Image:Eva millan.gif|[http://www.lcc.uma.es/~eva/ Eva Millán Valldeperas]
Image:Julita vasilleva.gif|[http://www.cs.usask.ca/faculty/julita/ Julita Vassileva]
Image:NicolaHenze.gif|[http://www.kbs.uni-hannover.de/~henze/ Nicola Henze]

</gallery>

== Past Master Students ==
<gallery perrow="4">
Image:Vikrant Khenat.jpg|[http://www.sis.pitt.edu/~vkhenat/ Vikrant Khenat]
Image:Tibor Dumitriu.gif|[http://www.sis.pitt.edu/~dumitriu/ Tibor Dumitriu] Projects: [http://ir.exp.sis.pitt.edu/advise/ AdVisE]
</gallery>

== Past Visiting Scholars ==
<gallery perrow="4">
Image:huhtamaki-jukka-300.jpg|[http://www.linkedin.com/in/jukkahuhtamaki Jukka Huhtamäki] Postdoc Researcher, DSc (Tech), University of Tampere
Image:Andrew.jpg|Shuchen Li (Andrew) From Beijing University of Posts and Telecommunications
Image:Rafael.png|[https://rafaelrda.wordpress.com Rafael Dias Araújo]
Image:Liping_wang.jpg|Liping Wang From JiLin University
Image:Ayca cebi.jpg|[https://ktu.academia.edu/aycacebi Ayça ÇEBİ] From Karadeniz Technical University
Image:File crop1 1183908 y 384.jpg|[https://people.aalto.fi/index.html?profilepage=isfor#!teemu_sirkia Teemu Sirkiä]
Image:Michelle_liang.JPG|[http://www.tcs.fudan.edu.cn/~michelle/index.html Michelle Liang]
Image:Pkraker.jpg|[http://science20.wordpress.com Peter Kraker] Marshall Plan Scholar
Image:Kim.jpg|Jaekyung Kim
Image:Jbravo.gif|[http://www.eps.uam.es/esp/personal/ficha.php?empid=367 Javier Bravo Agapito]
Image:MarkusKetterl1.jpg|[http://studip.serv.uni-osnabrueck.de/extern.php?username=mketterl&page_url=http://www.virtuos.uni-osnabrueck.de/VirtUOS/TemplStudipMitarbDetails&global_id=4c8fb9ddd4dde83366119b2031d39ab3 Markus Ketterl]
Image:Jillfreyne.jpg|[http://www.csi.ucd.ie/users/jill-freyne Jill Freyne]
Image:Robert.jpg|Robert Mertens
Image:Roman bednarik.png|[http://www.cs.joensuu.fi/~rbednari/ Roman bednarik]
Image:Ewald ramp.jpg|Ewald W. A. Ramp
Image:Jacopo.jpg|Jacopo Armani
Image:Yetunde.JPG|Yetunde Folajimi
Image:Chris_face.jpg|[http://www.austria-lexikon.at/af/User/Trattner%20Christoph Christof Trattner]
</gallery>

People

2019-03-01T18:44:11Z

Jbarriapineda: Delete squares from the photos

== Faculty ==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
</gallery>

== Doctoral Students ==
<gallery perrow="4" mode="nolines">
Image:Tsai.jpg|[http://www.cht77.com/ Chun-Hua Tsai]
Image:Avatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Kamil.jpg|[http://pitt.edu/~kaa108 Kamil Akhuseyinoglu]
Image:zrisha.png|[https://zakrisha.com Zak Risha]
Image:behnam.jpg|[http://pitt.edu/~ber58 Behnam Rahdari]
Image:k.thaker.png|[http://pitt.edu/~kmt81 Khushboo Thaker]
</gallery>

== Visiting Scholars ==
<gallery perrow="4">

</gallery>

== Past Doctoral Students ==
<gallery perrow="4">
Image:Roya.jpg|[[User:R.hosseini | Roya Hosseini]]
Image:yunhuang.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:Julio.jpg|[[User:Julio | Julio Guerra]]
Image:xidao.jpg|[[User:Xidao| Xidao Wen]]
Image:Shaghayeghsahebi.jpg|[[User:Sherry | Shaghayegh Sahebi (Sherry)]] Currently Assistant Professor in the Computer Science Department at State University of New York (SUNY) at Albany
Image:Clau.JPG|[[User:Clau | Claudia López]] Currently Assistant Professor in the Departamento de Informática, Universidad Técnica Federico Santa María, Chile
Image:Kong.png|[[User:Chirayu | Chirayu Wongchokprasitti]] Currently at the Department of Biomedical Informatics, University of Pittsburgh
Image:jennifer.jpg|[[User:Jennifer | Jennifer (Yiling) Lin]] Currently Assistant Professor in the department of Information Management at the National Sun Yat-Sen University.
Image:Denis_PAWS_blog.jpg|[[User:Dparra | Denis Parra]] Currently Assistant Professor at the Computer Science Department, School of Engineering at PUC Chile.
Image:jaewook-1.jpg|[[User:Jahn | Jae-wook Ahn]] Projects: [[ADVISE]], [[Adaptive VIBE]], [[YourNews]], [[YourSports]], [[TaskSieve]], [[NameSieve]] Research Staff Member, Cognitive Sciences and Education,IBM Research
Image:RostaFarzan.jpg|[[User:Rostaf | Rosta Farzan]] Currently Assistant Professor at School of Computing and Information, University of Pittsburgh.
Image:Michael_V_Yudelson.gif|'''[[User:Myudelson | Michael V. Yudelson]]''' Projects: [[Knowledge Tree]], [[CUMULATE]], [[PERSEUS]], [[NavEx]], [[CoPE]], [[WebEx]] Currently Postdoctoral Fellow at Carnegie Mellon University
Image:Sergey.jpg|[[User:Sergey | Sergey Sosnovsky]] Currently Assistant Professor at Utrecht University (the Netherlands)
Image:Hsiao.jpg|[[User:Shoha99 | Sharon (I-Han) Hsiao]] Projects: [[AnnotEx]], [[QuizJET]], [[Progressor]], [[ProgressorPlus]] Currently Assistant Professor @ CIDSE, Arizona State University
Image:Danielle.gif|[[User:Suleehs | Danielle H. Lee]] Projects: [[Eventur]], [[Proactive]] Currently Assistant Professor at the Department of Software, Sangmyung University, Korea
</gallery>

== Past Visiting Faculty ==
<gallery perrow="4">
Image:Susan_bull.png|[https://www.researchgate.net/profile/Susan_Bull2 Susan Bull]
Image:Jaakko peltonen 215x296.jpg|[http://users.ics.aalto.fi/jtpelto// Jaakko Peltonen]
Image:IMG_0611.JPG|[http://www.dcs.warwick.ac.uk/~acristea/ Alexandra I. Cristea]
Image:Sibel.jpg|[http://sibelsomyurek.com/ Sibel Somyürek]
Image:KatrienVerbert.jpg|[http://people.cs.kuleuven.be/~katrien.verbert/KatrienVerbert/Katrien_Verbert.html Katrien Verbert]
Image:Roman bednarik.png|[http://cs.uef.fi/~rbednari/ Roman Bednarik]
Image:TanjaMitrovic.jpg|[http://www.cosc.canterbury.ac.nz/tanja.mitrovic/ Tanja Mitrovic]
Image:Eva millan.gif|[http://www.lcc.uma.es/~eva/ Eva Millán Valldeperas]
Image:Julita vasilleva.gif|[http://www.cs.usask.ca/faculty/julita/ Julita Vassileva]
Image:NicolaHenze.gif|[http://www.kbs.uni-hannover.de/~henze/ Nicola Henze]

</gallery>

== Past Master Students ==
<gallery perrow="4">
Image:Vikrant Khenat.jpg|[http://www.sis.pitt.edu/~vkhenat/ Vikrant Khenat]
Image:Tibor Dumitriu.gif|[http://www.sis.pitt.edu/~dumitriu/ Tibor Dumitriu] Projects: [http://ir.exp.sis.pitt.edu/advise/ AdVisE]
</gallery>

== Past Visiting Scholars ==
<gallery perrow="4">
Image:huhtamaki-jukka-300.jpg|[http://www.linkedin.com/in/jukkahuhtamaki Jukka Huhtamäki] Postdoc Researcher, DSc (Tech), University of Tampere
Image:Andrew.jpg|Shuchen Li (Andrew) From Beijing University of Posts and Telecommunications
Image:Rafael.png|[https://rafaelrda.wordpress.com Rafael Dias Araújo]
Image:Liping_wang.jpg|Liping Wang From JiLin University
Image:Ayca cebi.jpg|[https://ktu.academia.edu/aycacebi Ayça ÇEBİ] From Karadeniz Technical University
Image:File crop1 1183908 y 384.jpg|[https://people.aalto.fi/index.html?profilepage=isfor#!teemu_sirkia Teemu Sirkiä]
Image:Michelle_liang.JPG|[http://www.tcs.fudan.edu.cn/~michelle/index.html Michelle Liang]
Image:Pkraker.jpg|[http://science20.wordpress.com Peter Kraker] Marshall Plan Scholar
Image:Kim.jpg|Jaekyung Kim
Image:Jbravo.gif|[http://www.eps.uam.es/esp/personal/ficha.php?empid=367 Javier Bravo Agapito]
Image:MarkusKetterl1.jpg|[http://studip.serv.uni-osnabrueck.de/extern.php?username=mketterl&page_url=http://www.virtuos.uni-osnabrueck.de/VirtUOS/TemplStudipMitarbDetails&global_id=4c8fb9ddd4dde83366119b2031d39ab3 Markus Ketterl]
Image:Jillfreyne.jpg|[http://www.csi.ucd.ie/users/jill-freyne Jill Freyne]
Image:Robert.jpg|Robert Mertens
Image:Roman bednarik.png|[http://www.cs.joensuu.fi/~rbednari/ Roman bednarik]
Image:Ewald ramp.jpg|Ewald W. A. Ramp
Image:Jacopo.jpg|Jacopo Armani
Image:Yetunde.JPG|Yetunde Folajimi
Image:Chris_face.jpg|[http://www.austria-lexikon.at/af/User/Trattner%20Christoph Christof Trattner]
</gallery>

Seminars

2019-02-26T22:41:49Z

Jbarriapineda:

Seminars

2019-02-26T22:41:21Z

Jbarriapineda:

Seminars

2019-02-26T22:41:05Z

Jbarriapineda:

Seminars

2019-02-26T22:39:47Z

Jbarriapineda:

Seminars

2019-02-26T22:38:37Z

Jbarriapineda:

Seminars

2019-02-26T22:31:53Z

Jbarriapineda:

Seminars

2019-02-26T22:30:32Z

Jbarriapineda:

Seminars

2019-02-26T22:20:37Z

Jbarriapineda:

Seminars

2019-02-26T22:20:21Z

Jbarriapineda:

Seminars

2019-02-26T22:19:13Z

Jbarriapineda: Created page with "<html> <iframe src="https://docs.google.com/spreadsheets/d/e/2PACX-1vTlIjx8JVsG4T26vwcm8_9KAaRvkOPOYcS-dvP1zkxC9MqcByC5f-o7s215O0dDcckRP28D1Id1J0GR/pubhtml?gid=0&single=tr..."

Open Corpus Personalized Learning

2016-12-05T15:12:09Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
{|
|valign="top" | [[ Image:Knowledge-linking-Illustration.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" |
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.
|}

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

In order to support students' learning in the classroom environment, we have implemented a web platform for students to access class materials including textbooks, research publications, web tutorials, etc. More importantly, the system automatically records users' reading behaviors in order to be able to build their student models based on this data. By now, the reading system is able to render material in two formats:
* Image-based
* HTML-based (not tested yet in classroom studies)
We plan to support pdf document rendering soon.

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|The experimental Reading System.]]

The reading system is basically formed by 2 main parts:
* The reader itself (see right side of the figure)
* The student reading data section (see left side of the figure)

In the student reading data section, the users can have access to two information sources. The first one is a sunburst hierarchical visualization tool (see upper section) that allows them to know their progress in the reading of the contents that are associated with the course using a color scale encoding from red (non-read) to green (totally read). The former version of this visualization tool is called [[ReadingCircle]].
The second one (see lower section) is the hierarchical index of the group, where each section
The system is created for including learning material following a hierarchical structure in a similar way as books are structured (chapter, subchapter, section, etc.). In addition to this, the system allows the inclusion of multiple choice questions at the end of each section with the aim of test the acquired knowledge of the students.

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).
* Meng, Rui and Han, Shuguang and Huang, Yun and He, Daqing and Brusilovsky, Peter. "Knowledge-based Content Linking for Online Textbooks." In Proceeding of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 13-16. IEEE Computer Society, 2016. ([http://d-scholarship.pitt.edu/30486/1/wi16-knowledge-linking.pdf paper]).

Open Corpus Personalized Learning

2016-12-05T11:51:32Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
{|
|valign="top" | [[ Image:Knowledge-linking-Illustration.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" |
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.
|}

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

In order to support students' learning in the classroom environment, we have implemented a web platform for students to access class materials including textbooks, research publications, web tutorials, etc. More importantly, the system automatically records users' reading behaviors in order to be able to build their student models based on this data. By now, the reading system is able to render material in two formats:
* Image-based
* HTML-based (not tested yet in classroom studies)
We plan to support pdf document rendering soon.

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|The experimental Reading System.]]

The reading system is basically formed by 2 main parts:
* The reader itself (see right side of the figure)
* The student reading data section (see left side of the figure)

In the student reading data section, the users can have access to two information sources. The first one is a sunburst hierarchical visualization tool (see upper section) that allows them to know their progress in the reading of the contents that are associated with the course using a color scale encoding from red (non-read) to green (totally read). This visualization tool is called ReadingCircle.
The second one (see lower section) is the hierarchical index of the group, where each section
The system is created for including learning material following a hierarchical structure in a similar way as books are structured (chapter, subchapter, section, etc.). In addition to this, the system allows the inclusion of multiple choice questions at the end of each section with the aim of test the acquired knowledge of the students.

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).
* Meng, Rui and Han, Shuguang and Huang, Yun and He, Daqing and Brusilovsky, Peter. "Knowledge-based Content Linking for Online Textbooks." In Proceeding of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 13-16. IEEE Computer Society, 2016. ([http://d-scholarship.pitt.edu/30486/1/wi16-knowledge-linking.pdf paper]).

Open Corpus Personalized Learning

2016-12-05T11:48:17Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
{|
|valign="top" | [[ Image:Knowledge-linking-Illustration.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" |
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.
|}

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

In order to support students' learning in the classroom environment, we have implemented a web platform for students to access class materials including textbooks, research publications, web tutorials, etc. More importantly, the system automatically records users' reading behaviors in order to be able to build their student models based on this data. By now, the reading system is able to render material in two formats:
* Image-based
* HTML-based (not tested yet in classroom studies)
(We plan to support pdf document rendering soon).

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|The experimental Reading System.]]

The reading system is basically formed by 2 main parts:
* The reader itself (see right side of the figure)
* The student reading data section (see left side of the figure)

In the student reading data section, the users can have access to two information sources. The first one is a sunburst hierarchical visualization tool (see upper section) that allows them to know their progress in the reading of the contents that are associated with the course using a color scale encoding (red->non-read, green->totally read). The second one (see lower section) is
The system is created for including learning material following a hierarchical structure in a similar way as books are structured (chapter, subchapter, section, etc.). In addition to this, the system allows the inclusion of multiple choice questions at the end of each section with the aim of test the acquired knowledge of the students.

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).
* Meng, Rui and Han, Shuguang and Huang, Yun and He, Daqing and Brusilovsky, Peter. "Knowledge-based Content Linking for Online Textbooks." In Proceeding of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 13-16. IEEE Computer Society, 2016. ([http://d-scholarship.pitt.edu/30486/1/wi16-knowledge-linking.pdf paper]).

Open Corpus Personalized Learning

2016-12-05T07:51:07Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
{|
|valign="top" | [[ Image:Knowledge-linking-Illustration.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" |
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.
|}

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

In order to support students' learning in the classroom environment, we have implemented a web platform for students to access class materials including textbooks, research publications, web tutorials, etc. More importantly, the system automatically records users' reading behaviors in order to be able to build their student models based on this data. By now, the reading system is able to render material in two formats (we plan to support pdf document rendering soon):This is page content.<ref>''LibreOffice For Starters'', First Edition, Flexible Minds, Manchester, 2002, p. 18</ref>
{{reflist}}
* Image-based
* HTML-based (not tested yet in classroom studies)

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|The experimental Reading System.]]

The reading system is basically formed by 2 main parts:
* The reader itself (see right side of the figure)
* The student reading data section (see left side of the figure)

In the student reading data section, the users can have access to two information sources. The first one is a sunburst hierarchical visualization tool (see upper section) that allows them to know their progress in the reading of the contents that are associated with the course using . The second one (see lower section) is
The system is created for including learning material following a hierarchical structure in a similar way as books are structured (chapter, subchapter, section, etc.). In addition to this, the system allows the inclusion of multiple choice questions at the end of each section with the aim of test the acquired knowledge of the students.

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).
* Meng, Rui and Han, Shuguang and Huang, Yun and He, Daqing and Brusilovsky, Peter. "Knowledge-based Content Linking for Online Textbooks." In Proceeding of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 13-16. IEEE Computer Society, 2016. ([http://d-scholarship.pitt.edu/30486/1/wi16-knowledge-linking.pdf paper]).

Open Corpus Personalized Learning

2016-12-05T07:35:33Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
{|
|valign="top" | [[ Image:Knowledge-linking-Illustration.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" |
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.
|}

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

In order to support students' learning in the classroom environment, we have implemented a web platform for students to access class materials including textbooks, research publications, web tutorials, etc. More importantly, the system automatically records users' reading behaviors in order to be able to build their student models based on this data. By now, the reading system is able to render material in two formats (we plan to support pdf document rendering soon.):
* Image-based
* HTML-based (not tested yet in classroom studies)

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|The experimental reading system.]]

The reading system is basically formed by 2 main parts:
* The reader itself (see right side of the figure )
* The student reading data section (see left side of the figure)

In the student reading data section the users can have access to two information sources. The first one is a sunburst hierarchical visualization tool (see superior section) that allows them to know their progress in the reading of the contents that are associated with the course using . The second one is
The system is created for including learning material following a hierarchical structure in a similar way as books are structured (chapter, subchapter, section, etc.). In addition to this, the system allows the inclusion of multiple choice questions at the end of each section with the aim of test the acquired knowledge of the students.

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).
* Meng, Rui and Han, Shuguang and Huang, Yun and He, Daqing and Brusilovsky, Peter. "Knowledge-based Content Linking for Online Textbooks." In Proceeding of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 13-16. IEEE Computer Society, 2016. ([http://d-scholarship.pitt.edu/30486/1/wi16-knowledge-linking.pdf paper]).

Open Corpus Personalized Learning

2016-12-05T06:13:39Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
{|
|valign="top" | [[ Image:Knowledge-linking-Illustration.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" |
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.
|}

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

In order to support students' learning in the classroom environment, we have implemented a web platform for students to access class materials including textbooks, research publications, web tutorials, etc. More importantly, the system automatically records users' reading behaviors in order to be able to build their student models based on this data. By now, the reading system is able to render material in two formats:
* Image-based
* HTML-based (not tested yet in classroom studies)
We plan to support pdf documents rendering soon.

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|The experimental reading system.]]

The system is created for including learning material following a hierarchical structure in a similar way as books are structured (chapter, subchapter, section, etc.). In addition to this, the system allows the inclusion of multiple choice questions at the end of each section with the aim of test the acquired knowledge of the students.
The reading system is basically formed by 2 main parts:
* The reader itself (see right side of Figure )
* The student reading information section (see left side of Figure)

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).
* Meng, Rui and Han, Shuguang and Huang, Yun and He, Daqing and Brusilovsky, Peter. "Knowledge-based Content Linking for Online Textbooks." In Proceeding of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 13-16. IEEE Computer Society, 2016. ([http://d-scholarship.pitt.edu/30486/1/wi16-knowledge-linking.pdf paper]).

Open Corpus Personalized Learning

2016-12-05T06:13:09Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
{|
|valign="top" | [[ Image:Knowledge-linking-Illustration.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" |
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.
|}

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

In order to support students' learning in the classroom environment, we have implemented a web platform for students to access class materials including textbooks, research publications, web tutorials, etc. More importantly, the system automatically records users' reading behaviors in order to be able to build their student models based on this data. By now, the reading system is able to render material in two formats:
* Image-based
* HTML-based (not tested yet in classroom studies)
We plan to support pdf documents rendering soon.

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|'Experimental Reading System.]]

The system is created for including learning material following a hierarchical structure in a similar way as books are structured (chapter, subchapter, section, etc.). In addition to this, the system allows the inclusion of multiple choice questions at the end of each section with the aim of test the acquired knowledge of the students.
The reading system is basically formed by 2 main parts:
* The reader itself (see right side of Figure )
* The student reading information section (see left side of Figure)

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).
* Meng, Rui and Han, Shuguang and Huang, Yun and He, Daqing and Brusilovsky, Peter. "Knowledge-based Content Linking for Online Textbooks." In Proceeding of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 13-16. IEEE Computer Society, 2016. ([http://d-scholarship.pitt.edu/30486/1/wi16-knowledge-linking.pdf paper]).

Open Corpus Personalized Learning

2016-12-05T06:11:29Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
{|
|valign="top" | [[ Image:Knowledge-linking-Illustration.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" |
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.
|}

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

In order to support students' learning in the classroom environment, we have implemented a web platform for students to access class materials including textbooks, research publications, web tutorials, etc. More importantly, the system automatically records users' reading behaviors in order to be able to build their student models based on this data. By now, the reading system is able to render material in two formats:
* Image-based
* HTML-based (not tested yet in classroom studies)
We plan to support pdf documents rendering soon.

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|The Wikipede edits ''[[Myriapoda]]''.]]

The system is created for including learning material following a hierarchical structure in a similar way as books are structured (chapter, subchapter, section, etc.). In addition to this, the system allows the inclusion of multiple choice questions at the end of each section with the aim of test the acquired knowledge of the students.
The reading system is basically formed by 2 main parts:
* The reader itself (see right side of Figure )
* The student reading information section (see left side of Figure)
The platform track the students' reading behavior (pages loads, scrollings, etc.) of the students in order

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).
* Meng, Rui and Han, Shuguang and Huang, Yun and He, Daqing and Brusilovsky, Peter. "Knowledge-based Content Linking for Online Textbooks." In Proceeding of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 13-16. IEEE Computer Society, 2016. ([http://d-scholarship.pitt.edu/30486/1/wi16-knowledge-linking.pdf paper]).

Open Corpus Personalized Learning

2016-12-05T06:10:41Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
{|
|valign="top" | [[ Image:Knowledge-linking-Illustration.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" |
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.
|}

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|The Wikipede edits ''[[Myriapoda]]''.]]

In order to support students' learning in the classroom environment, we have implemented a web platform for students to access class materials including textbooks, research publications, web tutorials, etc. More importantly, the system automatically records users' reading behaviors in order to be able to build their student models based on this data. By now, the reading system is able to render material in two formats:
* Image-based
* HTML-based (not tested yet in classroom studies)
We plan to support pdf documents rendering soon.

The system is created for including learning material following a hierarchical structure in a similar way as books are structured (chapter, subchapter, section, etc.). In addition to this, the system allows the inclusion of multiple choice questions at the end of each section with the aim of test the acquired knowledge of the students.
The reading system is basically formed by 2 main parts:
* The reader itself (see right side of Figure )
* The student reading information section (see left side of Figure)
The platform track the students' reading behavior (pages loads, scrollings, etc.) of the students in order

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).
* Meng, Rui and Han, Shuguang and Huang, Yun and He, Daqing and Brusilovsky, Peter. "Knowledge-based Content Linking for Online Textbooks." In Proceeding of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 13-16. IEEE Computer Society, 2016. ([http://d-scholarship.pitt.edu/30486/1/wi16-knowledge-linking.pdf paper]).

Open Corpus Personalized Learning

2016-12-05T06:06:45Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
{|
|valign="top" | [[ Image:Knowledge-linking-Illustration.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" |
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.
|}

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|The Wikipede edits ''[[Myriapoda]]''.]]

In order to support students' learning in the classroom environment, we have implemented a web platform for students to access class materials including textbooks, research publications, web tutorials, etc. More importantly, the system automatically records users' reading behaviors in order to be able to build their student models based on this data. By now, the reading system is able to render material in two formats:
* Image-based
* HTML-based (not tested yet in classroom studies)
We plan to support pdf document rendering soon.

The system is created for including learning material following a hierarchical structure in a similar way as books are structured (chapter, subchapter, section, etc.). In addition to provide this material, the system allows the inclusion of multiple choice questions at the end of each section with the aim of test the acquired knowledge of the students.
The reading system
The platform track the students' reading behavior (pages loads, scrollings, etc.) of the students in order

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).
* Meng, Rui and Han, Shuguang and Huang, Yun and He, Daqing and Brusilovsky, Peter. "Knowledge-based Content Linking for Online Textbooks." In Proceeding of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 13-16. IEEE Computer Society, 2016. ([http://d-scholarship.pitt.edu/30486/1/wi16-knowledge-linking.pdf paper]).

Open Corpus Personalized Learning

2016-12-05T06:06:27Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
{|
|valign="top" | [[ Image:Knowledge-linking-Illustration.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" |
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.
|}

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|The Wikipede edits ''[[Myriapoda]]''.]]

In order to support students' learning in the classroom environment, we have implemented a web platform for students to access class materials including textbooks, research publications, web tutorials, etc. More importantly, the system automatically records users' reading behaviors in order to be able to build their student models based on this data. By now, the reading system is able to render material in two formats:
* Image-based
* HTML-based (not tested yet in classroom studies)
We plan to support pdf document rendering soon.
The system is created for including learning material following a hierarchical structure in a similar way as books are structured (chapter, subchapter, section, etc.). In addition to provide this material, the system allows the inclusion of multiple choice questions at the end of each section with the aim of test the acquired knowledge of the students.
The reading system
The platform track the students' reading behavior (pages loads, scrollings, etc.) of the students in order

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).
* Meng, Rui and Han, Shuguang and Huang, Yun and He, Daqing and Brusilovsky, Peter. "Knowledge-based Content Linking for Online Textbooks." In Proceeding of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 13-16. IEEE Computer Society, 2016. ([http://d-scholarship.pitt.edu/30486/1/wi16-knowledge-linking.pdf paper]).

Open Corpus Personalized Learning

2016-12-05T06:05:13Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
{|
|valign="top" | [[ Image:Knowledge-linking-Illustration.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" |
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.
|}

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|The Wikipede edits ''[[Myriapoda]]''.]]

In order to support students' learning in the classroom environment, we have implemented a web platform for students to access class materials including textbooks, research publications, web tutorials, etc. More importantly, the system automatically records users' reading behaviors in order to be able to build their student models based on this data. By now, the platform is able to render material in two formats:
* Image-based
* HTML-based (not tested yet in classroom studies)
The system is created for including learning material following a hierarchical structure in a similar way as books are structured (chapter, subchapter, section, etc.).
In addition to provide the learning material, the system allows the inclusion of multiple choice questions at the end of each section with the aim of test the acquired knowledge of the students.
The reading system
The platform track the students' reading behavior (pages loads, scrollings, etc.) of the students in order

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).
* Meng, Rui and Han, Shuguang and Huang, Yun and He, Daqing and Brusilovsky, Peter. "Knowledge-based Content Linking for Online Textbooks." In Proceeding of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 13-16. IEEE Computer Society, 2016. ([http://d-scholarship.pitt.edu/30486/1/wi16-knowledge-linking.pdf paper]).

Open Corpus Personalized Learning

2016-12-05T06:01:23Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
{|
|valign="top" | [[ Image:Knowledge-linking-Illustration.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" |
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.
|}

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|The Wikipede edits ''[[Myriapoda]]''.]]

In order to support students' learning in the classroom environment, we have implemented a web platform for students to access class materials including textbooks, research publications, web tutorials, etc. More importantly, the system will automatically record users' reading behaviors in order to be able to build their student models based on this data.
* Image-based
* HTML-based (not tested yet in classroom studies)
The system is created for including learning material following a hierarchical structure in a similar way as books are structured (chapter, subchapter, section, etc.).
In addition to provide the learning material, the system allows the inclusion of multiple choice questions at the end of each section with the aim of test the acquired knowledge of the students.
The reading system
The platform track the students' reading behavior (pages loads, scrollings, etc.) of the students in order

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).
* Meng, Rui and Han, Shuguang and Huang, Yun and He, Daqing and Brusilovsky, Peter. "Knowledge-based Content Linking for Online Textbooks." In Proceeding of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 13-16. IEEE Computer Society, 2016. ([http://d-scholarship.pitt.edu/30486/1/wi16-knowledge-linking.pdf paper]).

Open Corpus Personalized Learning

2016-12-05T06:00:38Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
{|
|valign="top" | [[ Image:Knowledge-linking-Illustration.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" |
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.
|}

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|The Wikipede edits ''[[Myriapoda]]''.]]

In order to support students' learning in the classroom environment, we have implemented a web platform for students to access class materials including textbooks, research publications, web tutorials, etc. More importantly, the system will automatically record users' reading behaviors in order to be able to build their student models based on this data.
* Image-based
* HTML-based (not tested yet in classroom studies)
The system is created for including learning material following a hierarchical structure in a similar way as books are structured (chapter, subchapter, section, etc.).
In addition to provide the learning material, the system allows the inclusion of multiple choice questions at the end of each
The reading system
The platform track the students' reading behavior (pages loads, scrollings, etc.) of the students in order

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).
* Meng, Rui and Han, Shuguang and Huang, Yun and He, Daqing and Brusilovsky, Peter. "Knowledge-based Content Linking for Online Textbooks." In Proceeding of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 13-16. IEEE Computer Society, 2016. ([http://d-scholarship.pitt.edu/30486/1/wi16-knowledge-linking.pdf paper]).

Open Corpus Personalized Learning

2016-12-05T05:59:49Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
{|
|valign="top" | [[ Image:Knowledge-linking-Illustration.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" |
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.
|}

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|The Wikipede edits ''[[Myriapoda]]''.]]

In order to support students' learning in the classroom environment, we have implemented a web platform for students to access class materials including textbooks, research publications, web tutorials, etc. More importantly, the system will automatically record users' reading behaviors in order to be able to build the student models of learners.
* Image-based
* HTML-based (not tested yet in classroom studies)
The system is created for including learning material following a hierarchical structure in a similar way as books are structured (chapter, subchapter, section, etc.).
In addition to provide the learning material, the system allows the inclusion of multiple choice questions at the end of each
The reading system
The platform track the students' reading behavior (pages loads, scrollings, etc.) of the students in order

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).
* Meng, Rui and Han, Shuguang and Huang, Yun and He, Daqing and Brusilovsky, Peter. "Knowledge-based Content Linking for Online Textbooks." In Proceeding of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 13-16. IEEE Computer Society, 2016. ([http://d-scholarship.pitt.edu/30486/1/wi16-knowledge-linking.pdf paper]).

Open Corpus Personalized Learning

2016-12-05T05:18:33Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" |
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.
|}

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|The Wikipede edits ''[[Myriapoda]]''.]]

In order to support the students learning, we have implemented an initial web platform that let them to access two type of contents:
* Image-based
* HTML-based (not tested yet in classroom studies)
The system is created for including learning material following a hierarchical structure in a similar way as books are structured (chapter, subchapter, section, etc.).
In addition to provide the learning material, the system allows the inclusion of multiple choice questions at the end of each
The reading system
The platform track the students' reading behavior (pages loads, scrollings, etc.) of the students in order

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).
* Meng, Rui and Han, Shuguang and Huang, Yun and He, Daqing and Brusilovsky, Peter. "Knowledge-based Content Linking for Online Textbooks." In Proceeding of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 13-16. IEEE Computer Society, 2016. ([http://d-scholarship.pitt.edu/30486/1/wi16-knowledge-linking.pdf paper]).

Open Corpus Personalized Learning

2016-12-05T04:15:07Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|The Wikipede edits ''[[Myriapoda]]''.]]

In order to support the students learning, we have implemented an initial web platform that let them to access two type of contents:
* Image-based
* HTML-based (not tested yet in classroom studies)
The platform track the students' reading behavior (pages loads, scrollings, etc.) of the students in order to their student model.

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).
* Meng, Rui and Han, Shuguang and Huang, Yun and He, Daqing and Brusilovsky, Peter. "Knowledge-based Content Linking for Online Textbooks." In Proceeding of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 13-16. IEEE Computer Society, 2016. ([http://d-scholarship.pitt.edu/30486/1/wi16-knowledge-linking.pdf paper]).

Open Corpus Personalized Learning

2016-12-05T03:44:06Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|The Wikipede edits ''[[Myriapoda]]''.]]

In order to support the students learning, we have implemented an initial web platform that let them to access two type of contents:
* Image-based (
* HTML-based
The platform track the reading behavior (pages loads, scrolls) of the students in order to build their students model.

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).
* Meng, Rui and Han, Shuguang and Huang, Yun and He, Daqing and Brusilovsky, Peter. "Knowledge-based Content Linking for Online Textbooks." In Proceeding of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 13-16. IEEE Computer Society, 2016. ([http://d-scholarship.pitt.edu/30486/1/wi16-knowledge-linking.pdf paper]).

Open Corpus Personalized Learning

2016-12-05T02:56:57Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

In order to support the students learning, we have implemented an initial web platform that let them to access two type of contents:
* Image-based
* HTML-based

[[Image:ReadingSystem_122016.jpg|thumb|left|alt=Current reading platform.|The Wikipede edits ''[[Myriapoda]]''.]]

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).

Open Corpus Personalized Learning

2016-12-05T02:53:28Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

In order to support the students learning, we have implemented an initial web platform that let them to access two type of contents:
* Image-based
* HTML-based

[[Image:ReadingSystem_122016.jpg]]

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).

Open Corpus Personalized Learning

2016-12-05T02:52:42Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

In order to support the students learning, we have implemented an initial web platform that let them to access two type of contents:
* Image-based
* HTML-based

[[Image:ReadingSystem_122016.jpeg]]

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).

Open Corpus Personalized Learning

2016-12-05T02:52:26Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

In order to support the students learning, we have implemented an initial web platform that let them to access two type of contents:
* Image-based
* HTML-based

[[Image:ReadingCircle_122016.jpeg]]

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).

File:ReadingSystem 122016.jpg

2016-12-05T02:51:20Z

Jbarriapineda:

Open Corpus Personalized Learning

2016-12-05T02:46:46Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

In order to support the students learning, we have implemented an initial web platform that let them to access two type of contents:
* Image-based
* HTML-based

[[Image:ReadingCircle_12_2016.png]]

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).

Open Corpus Personalized Learning

2016-12-05T02:41:50Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

In order to support the students learning, we have implemented an initial web platform that let them to access two type of contents:
Image-based
HTML-based

[[Image:ReadingCircle_12_2016.png]]

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).

Open Corpus Personalized Learning

2016-12-05T02:37:09Z

Jbarriapineda: /* The Experimental Platform */

Goal: This project challenges the assumption that adaptive hypermedia systems require expensive knowledge engineering for domain and content modeling. It replaces carefully-crafted domain model with automatically-created domain models, lowering the cost of developing adaptive educational hypermedia software while also providing a wider range of instructional paths through the content. Adaptive educational hypermedia is known for its ability to improve learning outcomes and engagement maximizing educational opportunity for learners with different levels of knowledge. The development of this more automatic, open-corpus approach to adaptive educational hypermedia will increase the volume and the variety of resources available for meaningful online learning, especially for individuals learning on their own. Automatic knowledge indexing of educational content makes the system easy to maintain and update over time. These new open corpus user modeling techniques automatically adapt user models and personalized guidance to new materials as they are acquired. The ability to automatically organize, index, and adaptively recommend distributed educational content without the need of manual processing by system developers, enables new material to be integrated dynamically and with minimal effort in response to student needs.

This project merges research on text analysis, human learning, and personalization to enable open corpus personalized learning. It develops its models of the domain and human learning from an initial set of well-organized, manually selected materials. Automatic text analysis creates an ensemble of domain models with different characteristics. Each individual model may be flawed or incomplete, however collectively they provide comprehensive coverage of the topic from several perspectives, thus reducing the manual effort required to create adaptive educational hypermedia. Multiple perspectives also give the system more flexibility in how to guide each student. These domain models are used as a foundation for building and maintaining dynamic models of user knowledge. The ensemble of domain and user models is used to deliver reactive and proactive adaptive guidance in an open corpus context. The growth of a person's knowledge is inferred by observing learner behavior and obtaining occasional feedback. This exploratory research opens the way to open corpus personalized learning. The domain modeling, user modeling, and personalization techniques developed in this research will be evaluated using a multi-layer framework that includes assessment by subject experts, performance prediction, cross-validation, and user studies.

==The Project Team==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
Image:Daqing_He.png|'''[http://www.pitt.edu/~dah44/ Daqing He]''' Co-director
Image:Yun_Acadamic.png|[http://columbus.exp.sis.pitt.edu/yunhuang/index.htm Yun Huang]
Image:shuguang.png|[http://www.pitt.edu/~shh69/ Shuguang Han]
Image:rui.png|[http://memray.me/ Rui Meng]
Image:Sanqiang.png|[http://pitt.edu/~sanqiang Sanqiang Zhao]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
Image:Hungavatar.jpg|[http://pitt.edu/~hkc6 Hung Chau]
</gallery>

==Knowledge Extraction==
The Internet has dramatically increased both the volume and variety of online educational resources, such as online textbooks, online courses, and tutorials. The development of modern search techniques has further promoted the quick access of these resources. However, most of these educational resources are not well-structured, which imposed an important challenge -- readers without sufficient background knowledge may be difficult to understand its content. To achieve the goal of recommending ''the right content'' that matches individuals' knowledge levels, the first critical step is to provide a better organization for educational resources. The project visions two important components when organizing educational resources: (1) knowledge concept extraction; and (2) concept hierarchy extraction. Traditional solutions for these two problems heavily rely on experts' manual efforts which are time-consuming and unscalable.

Our goal for knowledge extraction is to provide a scalable solution for the above two problems. We pilot our study with extracting knowledge structures from textbooks since they provide a comprehensive list of concepts and are often used as major educational resources in schools, colleges and universities. In addition, textbooks are also equipped with structural information such as table of contents and glossaries, which are very helpful in identifying concepts and their relationships.

However, the automated extraction of knowledge concepts. Accurately extracting knowledge concepts from educational content is a challenge since the miss of a large-scale knowledge concept labels for building reliable machine learning algorithms. Considering the high time cost for expert-based labeling, we explore an alternative crowdsourcing-based, with restricted quality control, approach. That is, we distribute our knowledge concept labeling work to massive crowdsourcing workers, and further aggregate the obtained labels based on well-developed quality control methods in crowdsourcing. So far, we have built our annotation system and conducted several pilot studies. In the future, we would like to conduct a live experiment to examine the validity of this approach.

== Learner Modeling ==
{|
|valign="top" | [[Image:ReadingLearningProcess.png|thumb|left|'''100'''|Dynamic Knowledge Modeling in Textbook Reading]]
|valign="center" | We have recently proposed a data-driven framework for [[Dynamic Knowledge Modeling in Textbook-Based Learning| dynamic knowledge modeling in textbook-based learning]] (UMAP 2016). We formulated the problem of modeling learning from reading as a reading-time prediction problem, reconstructed existing popular student models (such as Knowledge Tracing) and explored two automatic text analysis approaches (bag-of-words-based and latent semantic-based) to build the KC model. This framework can be applied to a broader context of open-corpus personalized learning, empowering learners with the ability to access the right reading content at the right moment, despite the huge volume of online educational content. We are also working on applying [[Feature-Aware Student knowledge Tracing (FAST)|Feature-Aware Student knowledge Tracing (FAST)]] which is our new learner model proposed in 2014 with state-of-the-art predictive performance into textbook-based learning environment.

Over past years, our lab has developed [[CUMULATE]], a centralized user modeling server built for the [[ADAPT2]] architecture, to provide user modeling support for adaptive educational hypermedia (AEH) systems. We have proposed and implemented different learner models , including [[CUMULATE asymptotic knowledge assessment|asymptotic assessment of user knowledge]]. We have explored different aspects to improve learner modeling, including reducing the content model, better evaluation for practitioners and applying network (graph) analysis.

* [[Dynamic Knowledge Modeling in Textbook-Based Learning|More about dynamic knowledge modeling in textbook-based learning]]
* [[Learner Modeling|More about learner modeling]]
* [[Feature-Aware Student knowledge Tracing (FAST)|More about Feature-Aware Student knowledge Tracing (FAST)]]
* [[CUMULATE|More about CUMULATE]]
* [[CUMULATE asymptotic knowledge assessment|More about asymptotic assessment of user knowledge]]
|}

==The Experimental Platform==

In order to support the students learning, we have implemented an initial web platform that let them to access two type of contents:
Image-based
HTML-based

[[Image:ReadingCircle_12_2016.jpg]]

==Publications==
* Huang, Yun and Yudelson, Michael and Han, Shuguang and He, Daqing and Brusilovsky, Peter. "A Framework for Dynamic Knowledge Modeling in Textbook-Based Learning." In Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 141-150. ACM, 2016 ([http://d-scholarship.pitt.edu/28248/ paper]).

People

2016-10-18T15:14:46Z

Jbarriapineda: /* Doctoral Students */

== Faculty ==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
</gallery>

== Doctoral Students ==
<gallery perrow="4">
Image:Julio.jpg|[[User:Julio | Julio Guerra]]
Image:Roya.jpg|[[User:R.hosseini | Roya Hosseini]]
Image:xidao.jpg|[[User:Xidao| Xidao Wen]]
Image:yunhuang.png|[[User:Yuh43| Yun Huang]]
Image:Tsai.jpg|[http://www.cht77.com/ Chun-Hua Tsai]
Image:Avatar.jpg|[http://pitt.edu/~hkc6/index.html/ Hung Chau]
Image:Jordan.jpeg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
</gallery>

== Visiting Scholars ==
<gallery perrow="4">
Image:Rafael.png|[https://rafaelrda.wordpress.com Rafael Dias Araújo]
Image:Liping_wang.jpg|Liping Wang From JiLin University
Image:Ayca cebi.jpg|[https://ktu.academia.edu/aycacebi Ayça ÇEBİ] From Karadeniz Technical University
</gallery>

== Past Doctoral Students ==
<gallery perrow="4">
Image:Shaghayeghsahebi.jpg|[[User:Sherry | Shaghayegh Sahebi (Sherry)]] Currently Assistant Professor in the Computer Science Department at State University of New York (SUNY) at Albany
Image:Clau.JPG|[[User:Clau | Claudia López]]
Image:Kong.png|[[User:Chirayu | Chirayu Wongchokprasitti]]
Image:jennifer.jpg|[[User:Jennifer | Jennifer (Yiling) Lin]] Currently Assistant Professor in the department of Information Management at the National Sun Yat-Sen University.
Image:Denis_PAWS_blog.jpg|[[User:Dparra | Denis Parra]] Currently Assistant Professor at the Computer Science Department, School of Engineering at PUC Chile.
Image:jaewook-1.jpg|[[User:Jahn | Jae-wook Ahn]] Projects: [[ADVISE]], [[Adaptive VIBE]], [[YourNews]], [[YourSports]], [[TaskSieve]], [[NameSieve]] Research Staff Member, Cognitive Sciences and Education,IBM Research
Image:RostaFarzan.jpg|[[User:Rostaf | Rosta Farzan]] Currently Assistant Professor at School of Information Sciences.
Image:Michael_V_Yudelson.gif|'''[[User:Myudelson | Michael V. Yudelson]]''' Projects: [[Knowledge Tree]], [[CUMULATE]], [[PERSEUS]], [[NavEx]], [[CoPE]], [[WebEx]] Currently Postdoctoral Fellow at Carnegie Mellon University
Image:Sergey.jpg|[[User:Sergey | Sergey Sosnovsky]] Currently Principal Researcher, Head of the Intelligent e-Learning Technology Lab, CeLTech, DFKI
Image:Hsiao.jpg|[[User:Shoha99 | Sharon (I-Han) Hsiao]] Projects: [[AnnotEx]], [[QuizJET]], [[Progressor]], [[ProgressorPlus]] Currently Assistant Professor @ CIDSE, Arizona State University
Image:Danielle.gif|[[User:Suleehs | Danielle H. Lee]] Projects: [[Eventur]], [[Proactive]] Currently Assistant Professor at the University of Washington
</gallery>

== Past Visiting Faculty ==
<gallery perrow="4">
Image:Jaakko peltonen 215x296.jpg|[http://users.ics.aalto.fi/jtpelto// Jaakko Peltonen]
Image:IMG_0611.JPG|[http://www.dcs.warwick.ac.uk/~acristea/ Alexandra I. Cristea]
Image:Sibel.jpg|[http://sibelsomyurek.com/ Sibel Somyürek]
Image:KatrienVerbert.jpg|[http://people.cs.kuleuven.be/~katrien.verbert/KatrienVerbert/Katrien_Verbert.html Katrien Verbert]
Image:Roman bednarik.png|[http://cs.uef.fi/~rbednari/ Roman Bednarik]
Image:TanjaMitrovic.jpg|[http://www.cosc.canterbury.ac.nz/tanja.mitrovic/ Tanja Mitrovic]
Image:Eva millan.gif|[http://www.lcc.uma.es/~eva/ Eva Millán Valldeperas]
Image:Julita vasilleva.gif|[http://www.cs.usask.ca/faculty/julita/ Julita Vassileva]
Image:NicolaHenze.gif|[http://www.kbs.uni-hannover.de/~henze/ Nicola Henze]

</gallery>

== Past Master Students ==
<gallery perrow="4">
Image:Vikrant Khenat.jpg|[http://www.sis.pitt.edu/~vkhenat/ Vikrant Khenat]
Image:Tibor Dumitriu.gif|[http://www.sis.pitt.edu/~dumitriu/ Tibor Dumitriu] Projects: [http://ir.exp.sis.pitt.edu/advise/ AdVisE]
</gallery>

== Past Visiting Scholars ==
<gallery perrow="4">
Image:File crop1 1183908 y 384.jpg|[https://people.aalto.fi/index.html?profilepage=isfor#!teemu_sirkia Teemu Sirkiä]
Image:Kim.jpg|Jaekyung Kim
Image:Jbravo.gif|[http://www.eps.uam.es/esp/personal/ficha.php?empid=367 Javier Bravo Agapito]
Image:MarkusKetterl1.jpg|[http://studip.serv.uni-osnabrueck.de/extern.php?username=mketterl&page_url=http://www.virtuos.uni-osnabrueck.de/VirtUOS/TemplStudipMitarbDetails&global_id=4c8fb9ddd4dde83366119b2031d39ab3 Markus Ketterl]
Image:Jillfreyne.jpg|[http://www.csi.ucd.ie/users/jill-freyne Jill Freyne]
Image:Robert.jpg|Robert Mertens
Image:Roman bednarik.png|[http://www.cs.joensuu.fi/~rbednari/ Roman bednarik]
Image:Ewald ramp.jpg|Ewald W. A. Ramp
Image:Jacopo.jpg|Jacopo Armani
Image:Yetunde.JPG|Yetunde Folajimi
Image:Chris_face.jpg|[http://www.austria-lexikon.at/af/User/Trattner%20Christoph Christof Trattner]
Image:Michelle_liang.JPG|[http://www.tcs.fudan.edu.cn/~michelle/index.html Michelle Liang]
Image:Pkraker.jpg|[http://science20.wordpress.com Peter Kraker] Marshall Plan Scholar

</gallery>

File:Jordan.jpeg

2016-10-18T15:13:14Z

Jbarriapineda:

People

2016-10-18T14:59:37Z

Jbarriapineda: /* Doctoral Students */

== Faculty ==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
</gallery>

== Doctoral Students ==
<gallery perrow="4">
Image:Julio.jpg|[[User:Julio | Julio Guerra]]
Image:Roya.jpg|[[User:R.hosseini | Roya Hosseini]]
Image:xidao.jpg|[[User:Xidao| Xidao Wen]]
Image:yunhuang.png|[[User:Yuh43| Yun Huang]]
Image:Tsai.jpg|[http://www.cht77.com/ Chun-Hua Tsai]
Image:Avatar.jpg|[http://pitt.edu/~hkc6/index.html/ Hung Chau]
Image:Jordan.jpg|[http://pitt.edu/~jab464 Jordan Barria-Pineda]
</gallery>

== Visiting Scholars ==
<gallery perrow="4">
Image:Rafael.png|[https://rafaelrda.wordpress.com Rafael Dias Araújo]
Image:Liping_wang.jpg|Liping Wang From JiLin University
Image:Ayca cebi.jpg|[https://ktu.academia.edu/aycacebi Ayça ÇEBİ] From Karadeniz Technical University
</gallery>

== Past Doctoral Students ==
<gallery perrow="4">
Image:Shaghayeghsahebi.jpg|[[User:Sherry | Shaghayegh Sahebi (Sherry)]] Currently Assistant Professor in the Computer Science Department at State University of New York (SUNY) at Albany
Image:Clau.JPG|[[User:Clau | Claudia López]]
Image:Kong.png|[[User:Chirayu | Chirayu Wongchokprasitti]]
Image:jennifer.jpg|[[User:Jennifer | Jennifer (Yiling) Lin]] Currently Assistant Professor in the department of Information Management at the National Sun Yat-Sen University.
Image:Denis_PAWS_blog.jpg|[[User:Dparra | Denis Parra]] Currently Assistant Professor at the Computer Science Department, School of Engineering at PUC Chile.
Image:jaewook-1.jpg|[[User:Jahn | Jae-wook Ahn]] Projects: [[ADVISE]], [[Adaptive VIBE]], [[YourNews]], [[YourSports]], [[TaskSieve]], [[NameSieve]] Research Staff Member, Cognitive Sciences and Education,IBM Research
Image:RostaFarzan.jpg|[[User:Rostaf | Rosta Farzan]] Currently Assistant Professor at School of Information Sciences.
Image:Michael_V_Yudelson.gif|'''[[User:Myudelson | Michael V. Yudelson]]''' Projects: [[Knowledge Tree]], [[CUMULATE]], [[PERSEUS]], [[NavEx]], [[CoPE]], [[WebEx]] Currently Postdoctoral Fellow at Carnegie Mellon University
Image:Sergey.jpg|[[User:Sergey | Sergey Sosnovsky]] Currently Principal Researcher, Head of the Intelligent e-Learning Technology Lab, CeLTech, DFKI
Image:Hsiao.jpg|[[User:Shoha99 | Sharon (I-Han) Hsiao]] Projects: [[AnnotEx]], [[QuizJET]], [[Progressor]], [[ProgressorPlus]] Currently Assistant Professor @ CIDSE, Arizona State University
Image:Danielle.gif|[[User:Suleehs | Danielle H. Lee]] Projects: [[Eventur]], [[Proactive]] Currently Assistant Professor at the University of Washington
</gallery>

== Past Visiting Faculty ==
<gallery perrow="4">
Image:Jaakko peltonen 215x296.jpg|[http://users.ics.aalto.fi/jtpelto// Jaakko Peltonen]
Image:IMG_0611.JPG|[http://www.dcs.warwick.ac.uk/~acristea/ Alexandra I. Cristea]
Image:Sibel.jpg|[http://sibelsomyurek.com/ Sibel Somyürek]
Image:KatrienVerbert.jpg|[http://people.cs.kuleuven.be/~katrien.verbert/KatrienVerbert/Katrien_Verbert.html Katrien Verbert]
Image:Roman bednarik.png|[http://cs.uef.fi/~rbednari/ Roman Bednarik]
Image:TanjaMitrovic.jpg|[http://www.cosc.canterbury.ac.nz/tanja.mitrovic/ Tanja Mitrovic]
Image:Eva millan.gif|[http://www.lcc.uma.es/~eva/ Eva Millán Valldeperas]
Image:Julita vasilleva.gif|[http://www.cs.usask.ca/faculty/julita/ Julita Vassileva]
Image:NicolaHenze.gif|[http://www.kbs.uni-hannover.de/~henze/ Nicola Henze]

</gallery>

== Past Master Students ==
<gallery perrow="4">
Image:Vikrant Khenat.jpg|[http://www.sis.pitt.edu/~vkhenat/ Vikrant Khenat]
Image:Tibor Dumitriu.gif|[http://www.sis.pitt.edu/~dumitriu/ Tibor Dumitriu] Projects: [http://ir.exp.sis.pitt.edu/advise/ AdVisE]
</gallery>

== Past Visiting Scholars ==
<gallery perrow="4">
Image:File crop1 1183908 y 384.jpg|[https://people.aalto.fi/index.html?profilepage=isfor#!teemu_sirkia Teemu Sirkiä]
Image:Kim.jpg|Jaekyung Kim
Image:Jbravo.gif|[http://www.eps.uam.es/esp/personal/ficha.php?empid=367 Javier Bravo Agapito]
Image:MarkusKetterl1.jpg|[http://studip.serv.uni-osnabrueck.de/extern.php?username=mketterl&page_url=http://www.virtuos.uni-osnabrueck.de/VirtUOS/TemplStudipMitarbDetails&global_id=4c8fb9ddd4dde83366119b2031d39ab3 Markus Ketterl]
Image:Jillfreyne.jpg|[http://www.csi.ucd.ie/users/jill-freyne Jill Freyne]
Image:Robert.jpg|Robert Mertens
Image:Roman bednarik.png|[http://www.cs.joensuu.fi/~rbednari/ Roman bednarik]
Image:Ewald ramp.jpg|Ewald W. A. Ramp
Image:Jacopo.jpg|Jacopo Armani
Image:Yetunde.JPG|Yetunde Folajimi
Image:Chris_face.jpg|[http://www.austria-lexikon.at/af/User/Trattner%20Christoph Christof Trattner]
Image:Michelle_liang.JPG|[http://www.tcs.fudan.edu.cn/~michelle/index.html Michelle Liang]
Image:Pkraker.jpg|[http://science20.wordpress.com Peter Kraker] Marshall Plan Scholar

</gallery>

People

2016-10-18T14:53:42Z

Jbarriapineda: /* Past Doctoral Students */

== Faculty ==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
</gallery>

== Doctoral Students ==
<gallery perrow="4">
Image:Julio.jpg|[[User:Julio | Julio Guerra]]
Image:Roya.jpg|[[User:R.hosseini | Roya Hosseini]]
Image:xidao.jpg|[[User:Xidao| Xidao Wen]]
Image:yunhuang.png|[[User:Yuh43| Yun Huang]]
Image:Tsai.jpg|[http://www.cht77.com/ Chun-Hua Tsai]
Image:Avatar.jpg|[http://pitt.edu/~hkc6/index.html/ Hung Chau]
</gallery>

== Visiting Scholars ==
<gallery perrow="4">
Image:Rafael.png|[https://rafaelrda.wordpress.com Rafael Dias Araújo]
Image:Liping_wang.jpg|Liping Wang From JiLin University
Image:Ayca cebi.jpg|[https://ktu.academia.edu/aycacebi Ayça ÇEBİ] From Karadeniz Technical University
</gallery>

== Past Doctoral Students ==
<gallery perrow="4">
Image:Shaghayeghsahebi.jpg|[[User:Sherry | Shaghayegh Sahebi (Sherry)]] Currently Assistant Professor in the Computer Science Department at State University of New York (SUNY) at Albany
Image:Clau.JPG|[[User:Clau | Claudia López]]
Image:Kong.png|[[User:Chirayu | Chirayu Wongchokprasitti]]
Image:jennifer.jpg|[[User:Jennifer | Jennifer (Yiling) Lin]] Currently Assistant Professor in the department of Information Management at the National Sun Yat-Sen University.
Image:Denis_PAWS_blog.jpg|[[User:Dparra | Denis Parra]] Currently Assistant Professor at the Computer Science Department, School of Engineering at PUC Chile.
Image:jaewook-1.jpg|[[User:Jahn | Jae-wook Ahn]] Projects: [[ADVISE]], [[Adaptive VIBE]], [[YourNews]], [[YourSports]], [[TaskSieve]], [[NameSieve]] Research Staff Member, Cognitive Sciences and Education,IBM Research
Image:RostaFarzan.jpg|[[User:Rostaf | Rosta Farzan]] Currently Assistant Professor at School of Information Sciences.
Image:Michael_V_Yudelson.gif|'''[[User:Myudelson | Michael V. Yudelson]]''' Projects: [[Knowledge Tree]], [[CUMULATE]], [[PERSEUS]], [[NavEx]], [[CoPE]], [[WebEx]] Currently Postdoctoral Fellow at Carnegie Mellon University
Image:Sergey.jpg|[[User:Sergey | Sergey Sosnovsky]] Currently Principal Researcher, Head of the Intelligent e-Learning Technology Lab, CeLTech, DFKI
Image:Hsiao.jpg|[[User:Shoha99 | Sharon (I-Han) Hsiao]] Projects: [[AnnotEx]], [[QuizJET]], [[Progressor]], [[ProgressorPlus]] Currently Assistant Professor @ CIDSE, Arizona State University
Image:Danielle.gif|[[User:Suleehs | Danielle H. Lee]] Projects: [[Eventur]], [[Proactive]] Currently Assistant Professor at the University of Washington
</gallery>

== Past Visiting Faculty ==
<gallery perrow="4">
Image:Jaakko peltonen 215x296.jpg|[http://users.ics.aalto.fi/jtpelto// Jaakko Peltonen]
Image:IMG_0611.JPG|[http://www.dcs.warwick.ac.uk/~acristea/ Alexandra I. Cristea]
Image:Sibel.jpg|[http://sibelsomyurek.com/ Sibel Somyürek]
Image:KatrienVerbert.jpg|[http://people.cs.kuleuven.be/~katrien.verbert/KatrienVerbert/Katrien_Verbert.html Katrien Verbert]
Image:Roman bednarik.png|[http://cs.uef.fi/~rbednari/ Roman Bednarik]
Image:TanjaMitrovic.jpg|[http://www.cosc.canterbury.ac.nz/tanja.mitrovic/ Tanja Mitrovic]
Image:Eva millan.gif|[http://www.lcc.uma.es/~eva/ Eva Millán Valldeperas]
Image:Julita vasilleva.gif|[http://www.cs.usask.ca/faculty/julita/ Julita Vassileva]
Image:NicolaHenze.gif|[http://www.kbs.uni-hannover.de/~henze/ Nicola Henze]

</gallery>

== Past Master Students ==
<gallery perrow="4">
Image:Vikrant Khenat.jpg|[http://www.sis.pitt.edu/~vkhenat/ Vikrant Khenat]
Image:Tibor Dumitriu.gif|[http://www.sis.pitt.edu/~dumitriu/ Tibor Dumitriu] Projects: [http://ir.exp.sis.pitt.edu/advise/ AdVisE]
</gallery>

== Past Visiting Scholars ==
<gallery perrow="4">
Image:File crop1 1183908 y 384.jpg|[https://people.aalto.fi/index.html?profilepage=isfor#!teemu_sirkia Teemu Sirkiä]
Image:Kim.jpg|Jaekyung Kim
Image:Jbravo.gif|[http://www.eps.uam.es/esp/personal/ficha.php?empid=367 Javier Bravo Agapito]
Image:MarkusKetterl1.jpg|[http://studip.serv.uni-osnabrueck.de/extern.php?username=mketterl&page_url=http://www.virtuos.uni-osnabrueck.de/VirtUOS/TemplStudipMitarbDetails&global_id=4c8fb9ddd4dde83366119b2031d39ab3 Markus Ketterl]
Image:Jillfreyne.jpg|[http://www.csi.ucd.ie/users/jill-freyne Jill Freyne]
Image:Robert.jpg|Robert Mertens
Image:Roman bednarik.png|[http://www.cs.joensuu.fi/~rbednari/ Roman bednarik]
Image:Ewald ramp.jpg|Ewald W. A. Ramp
Image:Jacopo.jpg|Jacopo Armani
Image:Yetunde.JPG|Yetunde Folajimi
Image:Chris_face.jpg|[http://www.austria-lexikon.at/af/User/Trattner%20Christoph Christof Trattner]
Image:Michelle_liang.JPG|[http://www.tcs.fudan.edu.cn/~michelle/index.html Michelle Liang]
Image:Pkraker.jpg|[http://science20.wordpress.com Peter Kraker] Marshall Plan Scholar

</gallery>

People

2016-10-18T14:48:34Z

Jbarriapineda: /* Past Doctoral Students */

== Faculty ==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
</gallery>

== Doctoral Students ==
<gallery perrow="4">
Image:Julio.jpg|[[User:Julio | Julio Guerra]]
Image:Roya.jpg|[[User:R.hosseini | Roya Hosseini]]
Image:xidao.jpg|[[User:Xidao| Xidao Wen]]
Image:yunhuang.png|[[User:Yuh43| Yun Huang]]
Image:Tsai.jpg|[http://www.cht77.com/ Chun-Hua Tsai]
</gallery>

== Visiting Scholars ==
<gallery perrow="4">
Image:Rafael.png|[https://rafaelrda.wordpress.com Rafael Dias Araújo]
Image:Liping_wang.jpg|Liping Wang From JiLin University
Image:Ayca cebi.jpg|[https://ktu.academia.edu/aycacebi Ayça ÇEBİ] From Karadeniz Technical University
</gallery>

== Past Doctoral Students ==
<gallery perrow="4">
Image:Shaghayeghsahebi.jpg|[[User:Sherry | Shaghayegh Sahebi (Sherry)]]
Image:Clau.JPG|[[User:Clau | Claudia López]]
Image:Kong.png|[[User:Chirayu | Chirayu Wongchokprasitti]]
Image:jennifer.jpg|[[User:Jennifer | Jennifer (Yiling) Lin]] Currently Assistant Professor in the department of Information Management at the National Sun Yat-Sen University.
Image:Denis_PAWS_blog.jpg|[[User:Dparra | Denis Parra]] Currently Assistant Professor at the Computer Science Department, School of Engineering at PUC Chile.
Image:jaewook-1.jpg|[[User:Jahn | Jae-wook Ahn]] Projects: [[ADVISE]], [[Adaptive VIBE]], [[YourNews]], [[YourSports]], [[TaskSieve]], [[NameSieve]] Research Staff Member, Cognitive Sciences and Education,IBM Research
Image:RostaFarzan.jpg|[[User:Rostaf | Rosta Farzan]] Currently Assistant Professor at School of Information Sciences.
Image:Michael_V_Yudelson.gif|'''[[User:Myudelson | Michael V. Yudelson]]''' Projects: [[Knowledge Tree]], [[CUMULATE]], [[PERSEUS]], [[NavEx]], [[CoPE]], [[WebEx]] Currently Postdoctoral Fellow at Carnegie Mellon University
Image:Sergey.jpg|[[User:Sergey | Sergey Sosnovsky]] Currently Principal Researcher, Head of the Intelligent e-Learning Technology Lab, CeLTech, DFKI
Image:Hsiao.jpg|[[User:Shoha99 | Sharon (I-Han) Hsiao]] Projects: [[AnnotEx]], [[QuizJET]], [[Progressor]], [[ProgressorPlus]] Currently Assistant Professor @ CIDSE, Arizona State University
Image:Danielle.gif|[[User:Suleehs | Danielle H. Lee]] Projects: [[Eventur]], [[Proactive]] Currently Assistant Professor at the University of Washington
</gallery>

== Past Visiting Faculty ==
<gallery perrow="4">
Image:Jaakko peltonen 215x296.jpg|[http://users.ics.aalto.fi/jtpelto// Jaakko Peltonen]
Image:IMG_0611.JPG|[http://www.dcs.warwick.ac.uk/~acristea/ Alexandra I. Cristea]
Image:Sibel.jpg|[http://sibelsomyurek.com/ Sibel Somyürek]
Image:KatrienVerbert.jpg|[http://people.cs.kuleuven.be/~katrien.verbert/KatrienVerbert/Katrien_Verbert.html Katrien Verbert]
Image:Roman bednarik.png|[http://cs.uef.fi/~rbednari/ Roman Bednarik]
Image:TanjaMitrovic.jpg|[http://www.cosc.canterbury.ac.nz/tanja.mitrovic/ Tanja Mitrovic]
Image:Eva millan.gif|[http://www.lcc.uma.es/~eva/ Eva Millán Valldeperas]
Image:Julita vasilleva.gif|[http://www.cs.usask.ca/faculty/julita/ Julita Vassileva]
Image:NicolaHenze.gif|[http://www.kbs.uni-hannover.de/~henze/ Nicola Henze]

</gallery>

== Past Master Students ==
<gallery perrow="4">
Image:Vikrant Khenat.jpg|[http://www.sis.pitt.edu/~vkhenat/ Vikrant Khenat]
Image:Tibor Dumitriu.gif|[http://www.sis.pitt.edu/~dumitriu/ Tibor Dumitriu] Projects: [http://ir.exp.sis.pitt.edu/advise/ AdVisE]
</gallery>

== Past Visiting Scholars ==
<gallery perrow="4">
Image:File crop1 1183908 y 384.jpg|[https://people.aalto.fi/index.html?profilepage=isfor#!teemu_sirkia Teemu Sirkiä]
Image:Kim.jpg|Jaekyung Kim
Image:Jbravo.gif|[http://www.eps.uam.es/esp/personal/ficha.php?empid=367 Javier Bravo Agapito]
Image:MarkusKetterl1.jpg|[http://studip.serv.uni-osnabrueck.de/extern.php?username=mketterl&page_url=http://www.virtuos.uni-osnabrueck.de/VirtUOS/TemplStudipMitarbDetails&global_id=4c8fb9ddd4dde83366119b2031d39ab3 Markus Ketterl]
Image:Jillfreyne.jpg|[http://www.csi.ucd.ie/users/jill-freyne Jill Freyne]
Image:Robert.jpg|Robert Mertens
Image:Roman bednarik.png|[http://www.cs.joensuu.fi/~rbednari/ Roman bednarik]
Image:Ewald ramp.jpg|Ewald W. A. Ramp
Image:Jacopo.jpg|Jacopo Armani
Image:Yetunde.JPG|Yetunde Folajimi
Image:Chris_face.jpg|[http://www.austria-lexikon.at/af/User/Trattner%20Christoph Christof Trattner]
Image:Michelle_liang.JPG|[http://www.tcs.fudan.edu.cn/~michelle/index.html Michelle Liang]
Image:Pkraker.jpg|[http://science20.wordpress.com Peter Kraker] Marshall Plan Scholar

</gallery>

People

2016-10-18T14:47:16Z

Jbarriapineda: /* Doctoral Students */

== Faculty ==
<gallery>
Image:Peter.jpg|'''[[User:Peterb | Peter Brusilovsky]]''' Director
</gallery>

== Doctoral Students ==
<gallery perrow="4">
Image:Julio.jpg|[[User:Julio | Julio Guerra]]
Image:Roya.jpg|[[User:R.hosseini | Roya Hosseini]]
Image:xidao.jpg|[[User:Xidao| Xidao Wen]]
Image:yunhuang.png|[[User:Yuh43| Yun Huang]]
Image:Tsai.jpg|[http://www.cht77.com/ Chun-Hua Tsai]
</gallery>

== Visiting Scholars ==
<gallery perrow="4">
Image:Rafael.png|[https://rafaelrda.wordpress.com Rafael Dias Araújo]
Image:Liping_wang.jpg|Liping Wang From JiLin University
Image:Ayca cebi.jpg|[https://ktu.academia.edu/aycacebi Ayça ÇEBİ] From Karadeniz Technical University
</gallery>

== Past Doctoral Students ==
<gallery perrow="4">
Image:Clau.JPG|[[User:Clau | Claudia López]]
Image:Kong.png|[[User:Chirayu | Chirayu Wongchokprasitti]]
Image:jennifer.jpg|[[User:Jennifer | Jennifer (Yiling) Lin]] Currently Assistant Professor in the department of Information Management at the National Sun Yat-Sen University.
Image:Denis_PAWS_blog.jpg|[[User:Dparra | Denis Parra]] Currently Assistant Professor at the Computer Science Department, School of Engineering at PUC Chile.
Image:jaewook-1.jpg|[[User:Jahn | Jae-wook Ahn]] Projects: [[ADVISE]], [[Adaptive VIBE]], [[YourNews]], [[YourSports]], [[TaskSieve]], [[NameSieve]] Research Staff Member, Cognitive Sciences and Education,IBM Research
Image:RostaFarzan.jpg|[[User:Rostaf | Rosta Farzan]] Currently Assistant Professor at School of Information Sciences.
Image:Michael_V_Yudelson.gif|'''[[User:Myudelson | Michael V. Yudelson]]''' Projects: [[Knowledge Tree]], [[CUMULATE]], [[PERSEUS]], [[NavEx]], [[CoPE]], [[WebEx]] Currently Postdoctoral Fellow at Carnegie Mellon University
Image:Sergey.jpg|[[User:Sergey | Sergey Sosnovsky]] Currently Principal Researcher, Head of the Intelligent e-Learning Technology Lab, CeLTech, DFKI
Image:Hsiao.jpg|[[User:Shoha99 | Sharon (I-Han) Hsiao]] Projects: [[AnnotEx]], [[QuizJET]], [[Progressor]], [[ProgressorPlus]] Currently Assistant Professor @ CIDSE, Arizona State University
Image:Danielle.gif|[[User:Suleehs | Danielle H. Lee]] Projects: [[Eventur]], [[Proactive]] Currently Assistant Professor at the University of Washington
</gallery>

== Past Visiting Faculty ==
<gallery perrow="4">
Image:Jaakko peltonen 215x296.jpg|[http://users.ics.aalto.fi/jtpelto// Jaakko Peltonen]
Image:IMG_0611.JPG|[http://www.dcs.warwick.ac.uk/~acristea/ Alexandra I. Cristea]
Image:Sibel.jpg|[http://sibelsomyurek.com/ Sibel Somyürek]
Image:KatrienVerbert.jpg|[http://people.cs.kuleuven.be/~katrien.verbert/KatrienVerbert/Katrien_Verbert.html Katrien Verbert]
Image:Roman bednarik.png|[http://cs.uef.fi/~rbednari/ Roman Bednarik]
Image:TanjaMitrovic.jpg|[http://www.cosc.canterbury.ac.nz/tanja.mitrovic/ Tanja Mitrovic]
Image:Eva millan.gif|[http://www.lcc.uma.es/~eva/ Eva Millán Valldeperas]
Image:Julita vasilleva.gif|[http://www.cs.usask.ca/faculty/julita/ Julita Vassileva]
Image:NicolaHenze.gif|[http://www.kbs.uni-hannover.de/~henze/ Nicola Henze]

</gallery>

== Past Master Students ==
<gallery perrow="4">
Image:Vikrant Khenat.jpg|[http://www.sis.pitt.edu/~vkhenat/ Vikrant Khenat]
Image:Tibor Dumitriu.gif|[http://www.sis.pitt.edu/~dumitriu/ Tibor Dumitriu] Projects: [http://ir.exp.sis.pitt.edu/advise/ AdVisE]
</gallery>

== Past Visiting Scholars ==
<gallery perrow="4">
Image:File crop1 1183908 y 384.jpg|[https://people.aalto.fi/index.html?profilepage=isfor#!teemu_sirkia Teemu Sirkiä]
Image:Kim.jpg|Jaekyung Kim
Image:Jbravo.gif|[http://www.eps.uam.es/esp/personal/ficha.php?empid=367 Javier Bravo Agapito]
Image:MarkusKetterl1.jpg|[http://studip.serv.uni-osnabrueck.de/extern.php?username=mketterl&page_url=http://www.virtuos.uni-osnabrueck.de/VirtUOS/TemplStudipMitarbDetails&global_id=4c8fb9ddd4dde83366119b2031d39ab3 Markus Ketterl]
Image:Jillfreyne.jpg|[http://www.csi.ucd.ie/users/jill-freyne Jill Freyne]
Image:Robert.jpg|Robert Mertens
Image:Roman bednarik.png|[http://www.cs.joensuu.fi/~rbednari/ Roman bednarik]
Image:Ewald ramp.jpg|Ewald W. A. Ramp
Image:Jacopo.jpg|Jacopo Armani
Image:Yetunde.JPG|Yetunde Folajimi
Image:Chris_face.jpg|[http://www.austria-lexikon.at/af/User/Trattner%20Christoph Christof Trattner]
Image:Michelle_liang.JPG|[http://www.tcs.fudan.edu.cn/~michelle/index.html Michelle Liang]
Image:Pkraker.jpg|[http://science20.wordpress.com Peter Kraker] Marshall Plan Scholar

</gallery>