|
|
TCDL Bulletin
Current 2005
Volume 2 Issue 1
Video Recommendations for the Open Video Project
Johan Bollen
Research Library
Los Alamos National Laboratory
Los Alamos, NM
jbollen@lanl.gov |
Michael L. Nelson and Raquel Araujo
Department of Computer Science
Old Dominion University
Norfolk, VA
{mln, raraujo}@cs.odu.edu |
Gary Geisler
Graduate Scool of Library &
Information Science
Simmons College
Boston, MA
gary.geisler@simmons.edu |
We discuss a prototype recommender system constructed for the Open Video project web site. Sequences of video downloads are used to generate networks of video relationships. A spreading activation recommender system uses video networks derived from the Open Video logs to generate recommendations. Since this technique relies on user video downloads, the recommender system does not require extensive text metadata or image analysis techniques. We evaluate the performance of this technique relative to a VSM operating on video titles and a collaborative filtering technique.
For a larger view, click here.
|
For a larger view, click here.
|
For a larger view, click here.
|
For a larger view, click here.
|
For a larger view, click here.
|
For a larger view, click here.
|
For a larger view, click here.
|
© Copyright 2005 Johan Bollen, Michael L. Nelson, Raquel Araujo, and Gary Geisler
Some or all of these materials were previously published in the Proceedings of the 5th
ACM/IEEE-CS Joint Conference on Digital libraries, ACM
1-58113-876-8/05/0006.
Top | Contents
Previous Article
Next Article
Home | E-mail the Editor
|
