Research on Hotel Comment Emotion Analysis Based on BiLSTM and GRU
Tingting Wu, Gengsheng Zheng · 2021
Aiming at the problem that LSTM can not deal with the long-distance two-way semantic dependence, complex model calculation and long training time, this paper proposes a C-BiLG deep learning algorithm based on two-way LSTM and GRU for emotion analysis task. Two-way LSTM has fewer parameters and faster model training, which can effectively extract the deep-seated information of the text. The combination of BiLSTM and GRU can solve the problem of semantic dependence and gradient disappearance. According to the control experiment, the experimental results show that the algorithm can improve the accuracy and optimize the classification effect in the emotional analysis of hotel comment data set.