High-quality tweet generation for online behavior security management based on semantics measurement

Behavior security management refers to monitoring and guiding the user's opinions in online social networks to reduce their harmful influence to social public security. Pushing designed tweets with specific contains to them is one of the promising ways to solve this problem. In this paper, we developed a new method for high-quality supervision tweet generation, which not only considers the semantics of the tweets but also includes the supervision requirement of different aspects. Firstly, we collect millions of tweets of six typical events. Following, we construct a sentiment lexicon suitable for online behavior analysis, and we also construct a lexicon for tweet preprocessing and emotional score calculation. Secondly, to include the semantics during sentence similarity calculation, we employ the tweets collected to train the word2vec model and employ the sum of the word vectors in specific sentences to form the sentence vector. Finally, we employ the TextRank to generate the supervision tweet. Experimental results based on data collected showed that the proposed methods outperform other related traditional methods, which can be used for effective social security management.