Usage derived recommendations for a video digital library

We describe a minimalist methodology to develop usage-based recommender systems for multimedia digital libraries. A prototype recommender system based on this strategy was implemented for the Open Video Project, a digital library of videos that are freely available for download. Sequential patterns of video retrievals are extracted from the project’s web download logs and analyzed to generate a network of video relationships. A spreading activation algorithm locates video recommendations by searching for associative paths connecting query-related videos. We evaluate the performance of the resulting system relative to an item-based collaborative filtering technique operating on user profiles extracted from the same log data. r 2006 Elsevier Ltd. All rights reserved.

• Type: Journal
• Year: 2007
• Where: JNCA
• Authors: Johan Bollen, Michael L. Nelson, Gary Geisler, Raquel Araujo
• Keywords: JNCA 2007, Recommender System, Usage-based Recommender Systems, Video