Collaborative Filtering for Digital Libraries

Report written in support of a presentation at JCDL 2002

We would like to acknowledge Tammy Culter, Reyn Nakamoto,and Kami Vaniea for their hard work in making the TsunamiDigital Library happen. We would also like to acknowledge TimHolt and Anton Dragunov for their initial work on the digitallibrary portal software. This material is based upon worksupported by the National Science Foundation under Grant No.0133994 and the Gray Family Chair for Innovative LibraryServices at Oregon State University Foundation.

Can collaborative filtering be successfully applied to digitallibraries in a manner that improves the effectiveness of thelibrary? Collaborative filtering systems remove the limitation oftraditional content-based search interfaces by using individuals toevaluate and recommend information. We introduce an approachwhere a digital library user specifies their need in the form of aquestion, and is provided with recommendations of documentsbased on ratings by other users with similar questions. Using atestbed of the Tsunami Digital Library, we found evidence thatsuggests that collaborative filtering may decrease the number ofsearch queries while improving users’ overall perception of thesystem. We discuss the challenges of designing a collaborativefiltering system for digital libraries and then present ourpreliminary experimental results.