The Latest Research Progress of Personalized Information Recommend Based on the Tag

Abstract

In web2.0 era, tag marks that users have become from passive consumers into active information creators. Users can create and use any tags which represent their will freely on the Internet; they can also share all kinds of tags which other users have created. At the same time, personalized information recommendation can solve the problem of the flood of information, so how to conduct personalized information recommendation based on tags has become the focus of many scholars. This paper summarized three categories about the information recommendation model based on tags: Graph theory- based model, Tensor-based model and Topic-based model, then the author put forward the defects of the existing model and the problems that need to be solved in the future, such as how to reduce noise, how to use social network analysis method to study social tag system and so on.