The Algorithm of Short Message Hot Topic Detection Based on Feature Association

摘要

Aiming at the mobile short message (SMS) hot topic extraction, the text features and statistical regularity of SMS are analyzed in this study. The formal description of SMS hot topic is given and an algorithm of SMS hot topic extraction based on feature association analysis is proposed. According to the proposed algorithm, feature words of SMS can be clustered into different word bags by calculating the association degree of these feature words and the hot topic can be identified by means of word bags matching. Experiments results show that the proposed algorithm can detect the hot topic in the SMS messages effectively, which is useful to the analysis of SMS popular sentiments.