COLLABORATIVE FILTERING: A NEW APPROACH TO SEARCHING DIGITAL LIBRARIES

• Published in: New review of information networking 2004-11, Vol.10 (2), p.177-191
• Main Authors: Webster, Janet, Jung, Seikyung, Herlocker, Jon
• Format: Article
• Language: English
• Subjects: Computerized information storage and retrieval; Digital libraries; Exact sciences and technology; Information and communication sciences; Information retrieval systems; Information retrieval systems. Information and document management system; Information science. Documentation; Sciences and techniques of general use; Searching; User interface
• ISSN: 1361-4576; 1740-7869
• DOI: 10.1080/13614570500054229

At Oregon State University (OSU), the School of Electrical Engineering and Computer Science (EECS) and the OSU Libraries are working together on a project to improve the effectiveness and accessibility of digital information created and collected by academic libraries. This project focuses on making digital resources more accessible through an innovative search interface that incorporates collaborative filtering. New approaches to search interfaces will help make the growing wealth of online content more accessible and useful. This paper discusses the problem, explains how collaborative filtering works, describes the System for Electronic Recommendation Filtering (SERF), and then presents initial results from an installation in the OSU Libraries. The productive collaboration at OSU between the Libraries and EECS portends the future of development of search systems; by working together, we can harness the expertise of librarians, computer scientists, and information users to develop more useful search interfaces and increase access to the libraries' resources and services.