Research on Social Tags Recommendation Techniques Based on Content

Yang Song, Zhi-Li Liu, Li-Jie Liª¤

(College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China)ª¤ª¤ª¤



Abstract:

With the rapid development of the Internet, more and more people begin to pay attention to social tagging which is a flexible and efficient method for classification. How to retrieve tags from the huge tag library becomes a hot topic to research. Firstly, the existing systems of social tags and its recommendation principles used in Web 2.0 are introduced in this paper. Secondly, the existing techniques about tag recommendation are summarized, and their merits and demerits are analysed. In most techniques for tag recommendation only two dimensions ¡°resource-user¡± are considered. But there are three dimensions ¡°resource-user-tag¡± in recommendation system based on social tags. A new method of social tag recommendation based on content-Feature Vote Tagging (FVT) is proposed in this paper. Finally, several kinds of evaluation methods are used to assess the return results of methods. The experiment results show that the method proposed in this paper can satisfy the expectation of the user for the recommendation results.ª¤

Key words:  social tags  tag recommendation  content  feature  Web2.0ª¤

DOI£º10.11916/j.issn.1005-9113.2013.02.014

Clc Number:TP391

Fund: