Full Paper (7 pages)
Official AAAI published version
Author's version (2.06MB)
Collaborative tagging systems are now deployed extensively to help users share and organize resources. Tag prediction and recommendation systems generally model user behavior as research has shown that accuracy can be significantly improved by modeling users' preferences. However, these preferences are usually treated as constant over time, neglecting the temporal factor within users' interests. On the other hand, little is known about how this factor may influence prediction in social bookmarking systems. In this paper, we investigate the temporal dynamics of user interests in tagging systems and propose a user-tag-specific temporal interests model for tracking users' interests over time. Additionally, we analyze the phenomenon of topic switches in social bookmarking systems, showing that a temporal interests model can benefit from the integration of topic switch detection and that temporal characteristics of social tagging systems are different from traditional concept drift problems. We conduct experiments on three public datasets, demonstrating the importance of personalization and user-tag specialization in tagging systems. Experimental results show that our method can outperform state-of-the-art tag prediction algorithms. We also incorporate our model within existing content-based methods yielding significant improvements in performance.
In Proceedings of the Twenty-Fifth AAAI Conference on Artificial Intelligence, pages 1279-1285, San Francisco, August 2011.
© AAAI, 2011. This is the author's version of the work. Not for redistribution.
Back to Brian Davison's publications