Multi-channel Convolutional Neural Network with Sentiment Information for Sentiment Classification

The sentence-level sentiment classification is a classic topic of natural language processing, which aims to decide the sentiment tendency toward a sentence. However, previous studies ignore the significant role of words with sentimental tendencies in sentiment classification. In this paper, a sentiment information convolutional neural network (SI-CNN) model is proposed to break through this bottleneck problem. SI-CNN model contains three channels, where the first extracts original features from sentences, the second focuses on the words with sentiment tendencies, and the third is responsible for the categories and locations of the words with sentimental tendencies. We evaluate our model on three large-scale datasets. Experimental results show that the proposed SI-CNN outperforms other state-of-the-art deep neural networks and the introduction of sentiment information can improve the accuracy of sentiment classification. We also implement a series of exploratory experiments to prove the rationality of SI-CNN.