Convolutional Neural Networks for Chinese sentiment classification of social network
Jia He, Maoyang Zou, Ping Liu · 2017
For some Chinese complex sentences, sentiment classification is a challenge. Convolutional Neural Network was used to English sentiment classification by the researchers such as Kim, which achieved very good results. In the new framework designed in this paper, Convolutional Neural Network is used to extract the features of the word embedding and sequence features of word vectors based on lexicon in the Chinese social network, then two kinds of features are fused as the input of Support Vector Machine, finally sentiment tendency of Chinese text is judged. Experimental result shows it is better than the traditional Convolutional Neural Network on precision and F-Score for Chinese sentiment classification.