A Weibo Topic Tracking System based on K-means

This article studied weibo text representation. For the weibo features such as short, real-time, colloquialism and originality, in the original vector space model, we propose a suitable method for weibo text representation. Make all the content words as feature words after participation. And we proposed T-TFIDF weight calculation method according to the features of weibo. According to the vector space model, we proposed a weibo adaptive topic tracking methods based on K-means clustering. Simulation analysis shows that, the method can by comparing the similarity micro-blog and sub topic vector set, determine whether weibo belonging to the topic.