A Two-stage Personalized Recommendation in CTS Using Graph-Based Clustering

Collaborative tagging systems (CTS) enable Internet users to annotate for resources using custom tags, and the tags reflect the user interest and thus form a user profile. However, the flexibility of tagging brings large number of synonymous and polysemous tags which make the use of these profile information to personalize resource recommendation difficult. We propose to use graph-based clustering to form groups of semantically-related tags in the offline stage. Then in the online stage the tag clusters act as an intermediary between users and resource and are utilized to personalize the query results in CTS. 5-fold cross-validation is performed on two data sets, the results are compared with two other algorithms. Results show that the algorithm proposed demonstrate much better personalization measured by the F-value, whilst the effect is more miraculous in a multi-topic than in a single-topic CTS. This observation suggests that in a multi-topic CTS tag clustering such as proposed in this paper is an important strategy.