A novel method for recognizing emotions of weblog sentences

With plenty of online resources constantly increasing (like weblog, product reviews, news reviews, etc.), it is difficult to read them and obtain the useful information, especially emotion information. The emotion analysis on internet online information has received much attention from natural language processing field in recent years. In most existing works, single-label emotion analysis have been studied by many scientists, it often ignores the complexity of human feelings. This paper is dedicated to construct the multi-label emotion topic model for recognizing the complicated emotions of weblog sentences based on Chinese emotion corpus Ren-CECps. We employ latent topic variables and emotion variables to find complex emotions of the sentence. The results of experiments indicate that the model is reasonable and effective in recognizing the mixed emotions of weblog sentences.