TAG RECOMMENDATION BASED ON TAG-TOPIC MODEL

With the rapid increase of the social websites, most social tagging systems are allowing users to share and to label various kinds of resources with their favorite tags. However, the uncontrolled use of tags makes the resources attached with some irrelevant even noise tags. To solve the problem, this paper proposes a tag-topic model based approach to recommend tags for resources, which elicits latent topics from resources and maps new resources to these latent topics so as to recommend the most appropriate tags for the resources. The experimental results show the effectiveness of the proposed approach.