Sentiment Analysis of Network Comments Based on GCNN
Chen Huang, Gongshen Liu · Proceedings of the 2018 2nd International Conference on Computer Science and Artificial Intelligence · 2018
Recently, satisfactory performance has been achieved on sentiment analysis tasks by using recurrent neural network (RNN). As a derived model of RNN, gated recurrent units (GRU) model has a great advantage in dealing with long text sequence problems, while the performance is limited when working with short texts. Therefore, to effectively extract the contextual information of network comments, and take advantage of convolutional neural network (CNN) that can capture the local features, we propose a GCNN (gated convolutional neural network) model based on GRU and CNN. In this paper, we compare the proposed GCNN model with CNN and RNN models on standard datasets. Experiment results show that the GCNN model achieves state-of-the-art performance on the sentiment analysis tasks, with 94.9% and 90.0% F1-score on hotel comments (ChnSentiCorp) corpus and the IMDB corpus respectively.