Journal of Computer Applications ›› 2019, Vol. 39 ›› Issue (7): 1936-1941.DOI: 10.11772/j.issn.1001-9081.2018122477

• Artificial intelligence • Previous Articles     Next Articles

Text sentiment classification based on 1D convolutional hybrid neural network

CHEN Zhenghao, FENG Ao, HE Jia   

  1. School of Computer Science, Chengdu University of Information Technology, Chengdu Sichuan 610225, China
  • Received:2018-12-17 Revised:2019-02-12 Online:2019-07-10 Published:2019-03-29
  • Supported by:

    This work is partially supported by the Key Project of Applied Basic Research of Sichuan Science and Technology Department (2017JY0011).

基于一维卷积混合神经网络的文本情感分类

陈郑淏, 冯翱, 何嘉   

  1. 成都信息工程大学 计算机学院, 成都 610225
  • 通讯作者: 何嘉
  • 作者简介:陈郑淏(1993-),男,四川成都人,硕士研究生,CCF会员,主要研究方向:自然语言处理、深度学习;冯翱(1978-),男,四川广安人,副教授,博士,CCF会员,主要研究方向:信息检索、数据挖掘、机器学习;何嘉(1968-),女,四川成都人,教授,博士,CCF会员,主要研究方向:计算智能、人工智能。
  • 基金资助:

    四川省科技厅应用基础重点项目(2017JY0011)。

Abstract:

Traditional 2D convolutional models suffer from loss of semantic information and lack of sequential feature expression ability in sentiment classification. Aiming at these problems, a hybrid model based on 1D Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) was proposed. Firstly, 2D convolution was replaced by 1D convolution to retain richer local semantic features. Then, a pooling layer was used to reduce data dimension and the output was put into the recurrent neural network layer to extract sequential information between the features. Finally, softmax layer was used to realize the sentiment classification. The experimental results on multiple standard English datasets show that the proposed model has 1-3 percentage points improvement in classification accuracy compared with traditional statistical method and end-to-end deep learning method. Analysis of each component of network verifies the value of introduction of 1D convolution and recurrent neural network for better classification accuracy.

Key words: sentiment classification, Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), word embedding, deep learning

摘要:

针对情感分类中传统二维卷积模型对特征语义信息的损耗以及时序特征表达能力匮乏的问题,提出了一种基于一维卷积神经网络(CNN)和循环神经网络(RNN)的混合模型。首先,使用一维卷积替换二维卷积以保留更丰富的局部语义特征;再由池化层降维后进入循环神经网络层,整合特征之间的时序关系;最后,经过softmax层实现情感分类。在多个标准英文数据集上的实验结果表明,所提模型在SST和MR数据集上的分类准确率与传统统计方法和端到端深度学习方法相比有1至3个百分点的提升,而对网络各组成部分的分析验证了一维卷积和循环神经网络的引入有助于提升分类准确率。

关键词: 情感分类, 卷积神经网络, 循环神经网络, 词向量, 深度学习

CLC Number: