Acta Scientiarum Naturalium Universitatis Pekinensis ›› 2018, Vol. 54 ›› Issue (3): 459-465.DOI: 10.13209/j.0479-8023.2017.168

    Next Articles

Chinese Text Sentiment Classification by H-RNN-CNN

LUO Fan, WANG Houfeng   

  1. Institute of Computational Linguistics, Peking University, Beijing 100871
  • Received:2017-07-13 Revised:2017-11-27 Online:2018-05-20 Published:2018-05-20
  • Contact: WANG Houfeng, E-mail: wanghf(at)


罗帆, 王厚峰   

  1. 北京大学计算语言学研究所, 北京 100871
  • 通讯作者: 王厚峰, E-mail: wanghf(at)
  • 基金资助:
    国家社会科学基金(12&ZD227)和863 计划(2015AA015402)资助


The authors present a hierarchical neural network H-RNN-CNN as a general model to represent text in sentiment analysis. Firstly, since information may lose in long text, the authors divide the text by sentence and use them as middle layer. Secondly, recurrent neural network is used to process sequence and relationship across sentences is captured by convolutional neural network. Moreover, the effectiveness of the variants of recurrent neural network and the pre-trained embedding are discussed. Experiment results demonstrate that the approach works well on several datasets.

Key words: sentiment classification, deep learning, convolutional neural network, recurrent neural network

摘要: 中文情感分类; 深度学习; 卷积神经网络; 循环神经网络

CLC Number: