Personalized Search by a Multi-type and Multi-level User Profile in Folksonomy

With the development of the web 2.0 communities, more and more collaborative tagging systems become popular in recent years. Based on previous relevant works on the collaborative tagging system, this paper proposes a concept of a multi-type and multi-level user profile for improving the efficiency of personalized search. User profile consists of different types of resource attributes, and every type reflects multi-level favorites and nuisances from user. A detailed design process of user profile is presented in this paper. We propose a personalized search method by using the multi-type and multi-level user profile. Experimental results on a large real dataset demonstrate that the multi-type and multi-level user profile outperforms the baseline methods.