Download presentation
Presentation is loading. Please wait.
Published byCaroline Hudson Modified over 9 years ago
1
Funding provided by the National Science Foundation DLI-Phase 2 NSF Award #0002935 A Digital Library of Reusable Science and Math Resources for Undergraduate Education Recommendations in iLumina Gary Geisler (UNC), Dave McArthur and Sarah Giersch (Eduprise) Developing Recommendation Services for a Digital Library with Uncertain and Changing Data
2
iLumina’s Vision The situation: e-learning will create a huge demand for high-quality digital course content Publishers will meet some of this demand through ebooks Instructors will still need informal digital modules to complement and tailor ebooks to specific courses The opportunity: The Internet now provides a scalable way to implement peer- centric sharing of informal digital content iLumina is a digital library that will realize this opportunity
3
iLumina’s Main Themes Featuring diverse, small-scale SMETE resources, especially ones created by instructors Using IMS’s rich and standard metadata to describe resources Developing services underpinned by IMS metadata (e.g., recommendations as well as search and browse) Promoting reuse and repackaging of resources by faculty authors Implementing a partially centralized (metadata) and partly distributed (content) architecture
4
Existing Repositories … CSTCSECDLOther Individual Contributions iLumina Content Review Cataloging Tool final Informal Collections UNCW Mathwright … Other Mapping Tool Cataloging Tool iLumina Open * * Construction Services Community Services Search Services User metadata Architecture Overview Recommendations Personalizations Formal peer review User ratings/review General forums Suggestion Boxes Flexible Retrieval Browsing Faceted Search Basic Search Resource Integrator Author Cataloging Addison Wesley Physlets
5
Information Sources for Recommendations Data TypeDescription Resource Characteristics IMS metadata elements and values Resource Evaluation Minimal acceptability judgments Informal user ratings Formal peer reviews Resource Usage User downloads User resubmissions User ProfileDemographics Affiliations Areas of interest Service preferences QualityAvailability HighComplete VariablePartial LowPartial VariablePartial
6
Recommendation Schemes Scheme NameSourcesRule Simple WinnerEvaluation (User ratings or reviews) If a resource is highly rated, recommend it. Profile MatchCharacteristics & Profile If a resource matches areas of interests, recommend it Basic Content- based Self ratings & Characteristics If a resource is structurally similar to ones previously liked, recommend it. Basic Collaborative Filtering Self ratings & User ratings If a resource is liked by those with similar tastes, recommend it
7
Recommendation Schemes (continued) Scheme NameSourcesRule Weak Content- based Self usage & Characteristics If a resource is structurally similar to ones previously used, recommend it. Weak Collaborative Filtering Self usage & Other usage If a resource is used by those with similar downloads, recommend it Content-based Collaborative Filtering Self ratings & Characteristics & User ratings If a resource is similar to ones previously liked and liked by those with similar tastes, recommend it. Home RunSelf ratings & Characteristics & User ratings & Profile If a resource is similar to ones previously liked and liked by those with similar tastes, and matches areas of interest, recommend it.
8
Challenges to Recommendation Schemes How can multiple recommendation schemes be implemented? Do more specific schemes work better than less specific ones? How should the choice of schemes be conditioned by data source quality and quantity (costs and benefits)? How should multiple purposes be factored into recommendations?
9
Towards Solutions to Challenges Do natural experiments: –Evaluation, Use and Profile information will grow over time in iLumina –Test the efficacy of different schemas as data becomes richer –Devise schemes that effectively incorporate new information sources Consider extending profiles to include multiple purposes and goals –Index user ratings and usage data by purpose
10
References and Sources Our project website: http://www.ilumina-project.orghttp://www.ilumina-project.org Project papers on the site: –JCDL: Developing Recommendation Services for a Digital Library with Uncertain and Changing Data. Joint Conference on Digital Libraries (JCDL) –CACM: Towards a Sharable Digital Library of Reusable Teaching Resources: Roles for Rich Metadata Communications of the ACM, Special Digital Libraries Issue, April 2001 –JERIC: A Sharable Digital Library of Reusable Teaching Resources: Roles for Rich Metadata. Journal on Education Resources in Computing (JERIC). –JLibAdmin: Library Services Today and Tomorrow: Lessons from iLumina, a Digital Library for Creating and Sharing Teaching Resources. Journal of Library Administration.
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.