Semantics and Relativity Expansion Based on Tag Recommendation with Time Degradation

With the rapid development of the Intemet, information overload and isotropic becomes worse and worse. Personalized services system’s birth partly resolved this problem. The traditional recommendation methods, such as content based recommendation and collaborative filtering, do help a lot. However, to some extent, it couldn’t authentically understand the preference of users. Considered the limitations of the traditional methods, tag recommedation spring up. This paper makes expanded research based on tag reccommendation. With semantic matching, a certain tag turns to a similar tag set. Acording to co-occurence of tags, a tag is expended to a ralated tag set. Integrate these tag set to generate recommendation list is better than single tag recomendation by experimental observation. Besides, this paper also adopt time degradatioin aglorithm which improved the recommender’s accuracy and efficiency. Keywords-Tag Recommendation, Semantic Matching, Cooccourance, Time degradation