Difference between revisions of "News"

From PAWS Lab
Jump to: navigation, search
(<span id="2011-05-01">2011-05-01</span> :: Sharon received 2011 Allen Kent Award for Outstanding Contributions to the Graduate Program in Information Science)
(<span id="2011-11-30">2011-11-30</span> :: Sergey Sosnovsky Thesis Defence: Ontology-Based Open-Corpus Personalization for E-Learning)
Line 1: Line 1:
 
__NOTOC__
 
__NOTOC__
 +
==== <span id="2012-07-09">2012-07-09</span> :: [[User:shoha99 | Sharon Hsiao]] Thesis Defence: Navigation Support and Social Visualization for Personalized E-Learning  ====
 +
A large number of educational resources is now made available on the Web to support both regular classroom learning and online learning. However, the abundance of available content produced at least two problems: how to help students to find the most appropriate resources and how to engage them into using these resources and benefit from them. Personalized and social learning have been suggested as potential ways to address these problems.
 +
 +
This work attempts to combine the ideas of personalized and social learning by providing navigation support through an open social student modeling visualization. A series of classroom studies exploited the idea of the approach and revealed promising results, which demonstrated the personalized guidance and social visualization combined helped students to find the most relevant resources of parameterized self-assessment questions for Java programming. Thus, this dissertation extend the approach to a larger collection of learning objects for cross content navigation and verify its capability of supporting social visualization for personalized E-Learning.
 +
 +
The study results confirm that working with the non-mandatory system, students enhanced the learning quality in increasing their motivation and engagement. They successfully achieved better learning results. Meanwhile, incorporating a mixed collection of content in the open social student modeling visualizations effectively led the students to work at the right level of questions. Both strong and weak student worked with the appropriate levels of questions for their readiness accordingly and yielded a consistent performance across all three levels of complexities. Additionally, providing a more realistic content collection on the navigation supported open social student modeling visualizations results in a uniform performance in the group. The classroom study revealed a clear pattern of social guidance, where the stronger students left the traces for weaker ones to follow. The subjective evaluation confirms the design of the interface in terms of the content organization. Students’ positive responses also compliment the objective system usage data.
 +
 
==== <span id="2011-11-30">2011-11-30</span> :: [[User:Sergey | Sergey Sosnovsky]] Thesis Defence: Ontology-Based Open-Corpus Personalization for E-Learning  ====
 
==== <span id="2011-11-30">2011-11-30</span> :: [[User:Sergey | Sergey Sosnovsky]] Thesis Defence: Ontology-Based Open-Corpus Personalization for E-Learning  ====
 
Conventional closed-corpus adaptive information systems control limited sets of documents in fixed subject domains and cannot provide access to the content outside the system. Such restrictions contradict the requirements of today, when most of the information systems are implemented in the open document space of WWW and are expected to operate on the open-corpus content. In order to maintain personalized access to open-corpus documents, an adaptive system should be able to model the documents and the relations between the documents and the domain knowledge automatically and dynamically. This dissertation explores the problem of open-corpus personalization and semantic modeling of open-corpus content in the context of e-Learning. Information on WWW is not without structure. Many collections of online instructional material (tutorials, electronic books, digital libraries, etc.) have been provided with implicit knowledge models encoded in form of tables of content, indexes, headers of chapters, links between pages, and different styles of text fragments. The main dissertation approach tries to leverage this layer of hidden semantics by extracting and representing it as coarse-grained models of collections. A central domain ontology is used to maintain overlay modeling of studentsÕ knowledge and serves as a reference point for multiple collections of external instructional material. In order to establish the link between the ontology and the open-corpus content models a special ontology mapping algorithm has been developed.  The proposed approach has been applied in the Ontology-based Open-corpus Personalization Service (OOPS) that recommends and adaptively annotates online reading material. The domain of Java programming has been chosen for the proof-of-concept implementation. A controlled experiment has been organized to evaluate the developed adaptive system and the proposed approach overall. The results of the evaluation have demonstrated several significant learning effects of the implemented open-corpus personalization. The analysis of log-based data has also shown that the open-corpus version of the system is capable of providing personalization of similar quality to the close-corpus one. Such results indicate that the proposed approach supports fully-scale open-corpus personalization for e-Learning. Further research is required to verify if the approach remains effective in other subject domains and with other types of instructional content.
 
Conventional closed-corpus adaptive information systems control limited sets of documents in fixed subject domains and cannot provide access to the content outside the system. Such restrictions contradict the requirements of today, when most of the information systems are implemented in the open document space of WWW and are expected to operate on the open-corpus content. In order to maintain personalized access to open-corpus documents, an adaptive system should be able to model the documents and the relations between the documents and the domain knowledge automatically and dynamically. This dissertation explores the problem of open-corpus personalization and semantic modeling of open-corpus content in the context of e-Learning. Information on WWW is not without structure. Many collections of online instructional material (tutorials, electronic books, digital libraries, etc.) have been provided with implicit knowledge models encoded in form of tables of content, indexes, headers of chapters, links between pages, and different styles of text fragments. The main dissertation approach tries to leverage this layer of hidden semantics by extracting and representing it as coarse-grained models of collections. A central domain ontology is used to maintain overlay modeling of studentsÕ knowledge and serves as a reference point for multiple collections of external instructional material. In order to establish the link between the ontology and the open-corpus content models a special ontology mapping algorithm has been developed.  The proposed approach has been applied in the Ontology-based Open-corpus Personalization Service (OOPS) that recommends and adaptively annotates online reading material. The domain of Java programming has been chosen for the proof-of-concept implementation. A controlled experiment has been organized to evaluate the developed adaptive system and the proposed approach overall. The results of the evaluation have demonstrated several significant learning effects of the implemented open-corpus personalization. The analysis of log-based data has also shown that the open-corpus version of the system is capable of providing personalization of similar quality to the close-corpus one. Such results indicate that the proposed approach supports fully-scale open-corpus personalization for e-Learning. Further research is required to verify if the approach remains effective in other subject domains and with other types of instructional content.

Revision as of 19:22, 3 August 2012

2012-07-09 :: Sharon Hsiao Thesis Defence: Navigation Support and Social Visualization for Personalized E-Learning

A large number of educational resources is now made available on the Web to support both regular classroom learning and online learning. However, the abundance of available content produced at least two problems: how to help students to find the most appropriate resources and how to engage them into using these resources and benefit from them. Personalized and social learning have been suggested as potential ways to address these problems.

This work attempts to combine the ideas of personalized and social learning by providing navigation support through an open social student modeling visualization. A series of classroom studies exploited the idea of the approach and revealed promising results, which demonstrated the personalized guidance and social visualization combined helped students to find the most relevant resources of parameterized self-assessment questions for Java programming. Thus, this dissertation extend the approach to a larger collection of learning objects for cross content navigation and verify its capability of supporting social visualization for personalized E-Learning.

The study results confirm that working with the non-mandatory system, students enhanced the learning quality in increasing their motivation and engagement. They successfully achieved better learning results. Meanwhile, incorporating a mixed collection of content in the open social student modeling visualizations effectively led the students to work at the right level of questions. Both strong and weak student worked with the appropriate levels of questions for their readiness accordingly and yielded a consistent performance across all three levels of complexities. Additionally, providing a more realistic content collection on the navigation supported open social student modeling visualizations results in a uniform performance in the group. The classroom study revealed a clear pattern of social guidance, where the stronger students left the traces for weaker ones to follow. The subjective evaluation confirms the design of the interface in terms of the content organization. Students’ positive responses also compliment the objective system usage data.

2011-11-30 :: Sergey Sosnovsky Thesis Defence: Ontology-Based Open-Corpus Personalization for E-Learning

Conventional closed-corpus adaptive information systems control limited sets of documents in fixed subject domains and cannot provide access to the content outside the system. Such restrictions contradict the requirements of today, when most of the information systems are implemented in the open document space of WWW and are expected to operate on the open-corpus content. In order to maintain personalized access to open-corpus documents, an adaptive system should be able to model the documents and the relations between the documents and the domain knowledge automatically and dynamically. This dissertation explores the problem of open-corpus personalization and semantic modeling of open-corpus content in the context of e-Learning. Information on WWW is not without structure. Many collections of online instructional material (tutorials, electronic books, digital libraries, etc.) have been provided with implicit knowledge models encoded in form of tables of content, indexes, headers of chapters, links between pages, and different styles of text fragments. The main dissertation approach tries to leverage this layer of hidden semantics by extracting and representing it as coarse-grained models of collections. A central domain ontology is used to maintain overlay modeling of studentsÕ knowledge and serves as a reference point for multiple collections of external instructional material. In order to establish the link between the ontology and the open-corpus content models a special ontology mapping algorithm has been developed. The proposed approach has been applied in the Ontology-based Open-corpus Personalization Service (OOPS) that recommends and adaptively annotates online reading material. The domain of Java programming has been chosen for the proof-of-concept implementation. A controlled experiment has been organized to evaluate the developed adaptive system and the proposed approach overall. The results of the evaluation have demonstrated several significant learning effects of the implemented open-corpus personalization. The analysis of log-based data has also shown that the open-corpus version of the system is capable of providing personalization of similar quality to the close-corpus one. Such results indicate that the proposed approach supports fully-scale open-corpus personalization for e-Learning. Further research is required to verify if the approach remains effective in other subject domains and with other types of instructional content.

2011-07-15 :: Denis Parra earns a paper award in UMAP 2011

In the last conference of User Modeling, Adaptation and Personalization (UMAP 2011) Denis Parra won one of the 2 James Chen Best Student paper awards for his paper Walk The Talk: Analyzing the relation between implicit and explicit feedback for preference elicitation that he co-authored with Dr. Xavier Amatriain. In this paper, the authors present a study on the music domain with last.fm users, which results leads them to create a regression model that maps implicit information (such as playcounts and how recently a user listened to albums) with explicit information in the form of ratings. More details in the conference proceedings in Springer

2011-06-12 :: Peter Promoted to Rank of Full Professor

Congratulations to our head of PAWS lab! [Read more ]

2011-05-01 :: Sharon received 2011 Allen Kent Award for Outstanding Contributions to the Graduate Program in Information Science

She has worked with Dr. Glenn Ray several years in designing and teaching undergraduate courses. She's affiliated as teaching fellow and teaches in our school now.

2010-12-15 :: Peter received Google grant to work on Personalized Social Systems for Local Communities

The grant will support our efforts to increase user participation in social systems designed for local communities. In the course of the project will explore two innovative ideas for increasing participation. The first idea is to provide access to information “beyond the desktop,” by adding a mobile location-based interface to access information. This will increase both the number of active users and the volume of their contributions. The second idea is to provide personalized access to information to increase the chance to gather relevant information. This work will be based on two existing social systems that were developed and maintained by PAWs lab: the CoMeT system for sharing information about research talks at Carnegie Mellon and University of Pittsburgh and Eventur, a social system for recommending cultural events in the Pittsburgh area.

2010-09-17 :: Michael Yudelson's Thesis Defence: Providing Service-Based Personalization In An Adaptive Hypermedia System

The dissertation proposes a novel way of speeding the development of new adaptive hypermedia systems. The gist of the approach is to extract the adaptation functionality out of the adaptive hypermedia system, encapsulate it into a standalone system, and offer adaptation as a service to the client applications. Such a standalone adaptation provider reduces the development of adaptation functionality to configuration and compliance and as a result creates new adaptive systems faster and helps serve larger user populations with adaptively accessible content. [details] The electronic version of Michael Yudelson's dissertation has been approved by the School of Information Sciences. ETD is accessible worldwide from the online library catalog of the University of Pittsburgh (link).

2010-09-15 :: Peter Brusilovsky received NSF grant to work on Modeling and Visualization of Latent Communities

This EAGER grant will allow us to investigate how to model and visualize latent communities – those groups of people who form communities based on their similar interests. This work will consider how to elicit latent communities from various kinds of data about individuals available in the modern social Web and deliver the results in a manner suitable for interactive exploration through interactive visualizations. This will be one of the first attempts to use a variety of social Web data and approaches to community modeling. [details]

2010-09-08 :: Jae-wook's Thesis Defence: Adaptive Visualization for Focused Personalized Information Retrieval

Jae-wook Ahn's dissertation proposes to incorporate interactive visualization into personalized search in order to overcome the limitation. By combining the personalized search and the interactive visualization, we expect our approach will be able to help users to better explore the information space and locate relevant information more efficiently. [details]

2010-09-01 :: Peter Brusilovsky and Jung Sun Oh received NSF grant to work on Personalization and social networking for short-term communities

This one-year grant will support a project exploring personalization and social networking for short-term communities. Using academic research conferences as a test bed, our team will explore new methods to leverage information about user interests (available from multiple external resources) and develop techniques to facilitate use of existing social technologies. [details]

2010-08-15 :: SIGWeb Newsletter published an interview with Peter Brusilovsky

The Summer 2010 issue of SIGWeb Newsletter (a magazine of ACM Special Interest Group on Hypertext and the Web) published an interview with Peter Brusilovsky. The interview provides some personal view on research project performed at PAWS.

2010-07-01 :: Jae-wook has received Computing Inovation Fellowship

Jae-wook Ahn was chosen as a CIFellow (Computing Innovation Fellow) supported by the Computing Community Consortium (CCC), the Computing Research Association (CRA), and the National Science Foundation. Starting from the fall 2010, he is going to work with Dr. Ben Shneiderman at the Human Computer Interaction Lab, University of Maryland.

2010-05-01 :: Sergey has received EU Marie Curie International Incoming Fellowship

Sergey Sosnovsky's proposal for EU Marie Curie Fellowship is approved by the EU Research Executive Agency. The funding starts in July, 2010 and will last until July 2012. The project "Intelligent Support for Authoring Semantic Learning Content" will focus on implementation of author-friendly technologies for learning content development, including collaborative authoring support, metadata authoring support, open-corpus content discovery, interactivity authoring, and gap detection.

2009-06-27 :: Rosta receives her second James Chen Award

Rosta Farzan received James Chen Best Student Paper Award at the 12th International Conference on User Modelling, Adaptation and Personalization, UMAP2009, in Trento, Italy for the paper Social Navigation Support for Information Seeking: If You Build It, Will They Come? by Rosta Farzan and Peter Brusilovsky. This is her second James Chen Award, congratulations!

2009-06-26 :: PAWS Caught on UMAP 2009 Video

2009-05-28 :: Peter awarded honorary doctorate by the Slovak University of Technology in Bratislava

At a ceremony in Bratislava today, Peter Brusilovsky was honored by the Slovak University of Technology in Bratislava with the degree of Doctor honoris causa. The university, founded in 1937 in Bratislava, is one of the most significant institutions of higher education in Slovakia. Peter was selected for this recognition for "his contributions to the fields of Informatics and Information Technologies".

2008-07-31 :: Peter receives Best Paper Award at AH 2008

Peter Brusilovsky received Best Paper Award at the 5th International Conference on Adaptive Hypermedia and Adaptive Web-Based Systems, AH 2008, in Hannover, Germany for the paper Social Information Access for the Rest of Us: An Exploration of Social YouTube by Maurice Coyle, Jill Freyne, Peter Brusilovsky, and Barry Smyth

2007-06-28 :: Michael receives James Chen Best Student Paper Award at UM 2007

Michael Yudelson received James Chen Best Student Paper Award at the 11th International Conference on User Modelling, UM07, in Corfu, Greece for the paper A User Modeling Server for Contemporary Adaptive Hypermedia: an Evaluation of Push Approach to Evidence Propagation by Michael Yudelson, Peter Brusilovsky, and Vladimir Zadorozhny