The Recommendation System of Micro-Blog Topic Based on User Clustering

摘要

As a type of crowdsensing media, micro-blog has become an important crowdsensing place for a lot of real-time information dissemination and discussion. With the increasing of micro-blog users, there are more and more new topics emerging on this kind of platform, which has made the users difficult in finding out their own interesting topics. To solve this problem, this paper proposes a micro-blog topic recommendation system which can give corresponding suggestions/strategies for users. Firstly, the user relationship (i.e., a user adds a follow hyperlink to another user) in micro-blog can be effectively analyzed and saved to the user graph. In addition, an algorithm of computing user authority (which is similar to the idea of PageRank) is proposed to catch influential users based on the built user graph. Secondly, Topic Feature Graph (TFG) and User Micro-blog Feature Graph (UMFG) are respectively constructed based on the micro-blog text corpus of a topic and the micro-blog texts followed by a given user. Based on TFG and UMFG, User Topic Feature Vector (UTFV) and User Topic Feature Matrix (UTFM) can be achieved. After that, users' similarity is calculated based on the User Topic Feature Vector and User Topic Feature Matrix to realize the users clustering by the help of the hierarchical clustering algorithm. Incorporating topic heat degree and user authority, the recommendation algorithm is presented to realize Micro-blog topic personalized recommendation within user clustering set. Experiments show that our proposed recommendation system has a good accuracy which is up to 50.2%.