Goal-Directed Site-Independent Recommendations from Passive Observations
- Tingshao Zhu
- Russ Greiner, Dept of Computing Science; PI of AICML
- Gerald Haeubl, School of Business; University of Alberta
- Kevin Jewell, Alberta Ingenuity
- Bob Price
This paper introduces a novel method to find Web pages that satisfy the user's current information need. The method infers the user's need from the content of the pages the user hasvisited and the actions the user has applied to these pages.Unlike content-based systems that attempt to learn a user's long-term interests, our system learns user-independent patternsof behavior that identify the user's current informationneed, based on his/her current browsing session, then usesthis information to suggest specific pages intended to address this need. Our system learns these behavior patterns from labeled data collected during a five-week user study, involving over one hundred participants working on their day-to-day tasks. We tested this learned model in a second phase of this same study, and found that this model can effectively identifythe information needs of new users as they browse previously unseen pages, and that we can use this information to help them find relevant pages.
Citation
T. Zhu, R. Greiner, G. Haeubl, K. Jewell, B. Price. "Goal-Directed Site-Independent Recommendations from Passive Observations". National Conference on Artificial Intelligence (AAAI), Pittsburgh, pp 549-556, July 2005.Keywords: | machine learning, WebIC |
Category: | In Conference |
BibTeX
@incollection{Zhu+al:AAAI05, author = {Tingshao Zhu and Russ Greiner and Gerald Haeubl and Kevin Jewell and Bob Price}, title = {Goal-Directed Site-Independent Recommendations from Passive Observations}, Pages = {549-556}, booktitle = {National Conference on Artificial Intelligence (AAAI)}, year = 2005, }Last Updated: June 05, 2007
Submitted by Staurt H. Johnson