• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 人工智能与数据挖掘 • 上一篇    下一篇

基于改进型神经网络的影评文本情感分析算法

李俭兵1,2,3,刘栗材1,3   

  1. (1.重庆邮电大学通信与信息工程学院,重庆 400065;2.重庆信科设计有限公司,重庆 400021;
    3.重庆邮电大学通信新技术应用研究中心,重庆 400065)
  • 收稿日期:2019-03-19 修回日期:2019-04-18 出版日期:2019-12-25 发布日期:2019-12-25

A film criticism sentiment analysis algorithm
 based on improved neural network

LI Jian-bing1,2,3,LIU Li-cai1,3   

  1. (1.School of Telecommunication and Information Engineering,
    Chongqing University of Posts and Telecommunications,Chongqing 400065;
    2.Chongqing Information Technology Designing Company Limited,Chongqing 400021;
    3.Research Center of New Telecommunication Technology Applications,
    Chongqing University of Posts and Telecommunications,Chongqing 400065,China)
  • Received:2019-03-19 Revised:2019-04-18 Online:2019-12-25 Published:2019-12-25

摘要:

考虑到电影影评上下文信息带有固有的属性特征和语序不合理性等特点,提出CRCNN模型进行文本情感分析。为了减少噪音数据对分析的影响,对卷积神经网络进行改进,在输入层和卷积层之间引入了权重分布层对重要部分进行分析,减少噪音,使处理的特征得到提升。在卷积层中使用梯度下降法来求解训练参数时会引起梯度弥散或爆炸,为了解决此问题引入了门控机制。最后引入序列标注层,同时和神经网络学习的语义特征进行整体的优化求解。另外,利用字粒度词向量为特征,解决了歧义词的切分的同时学习到更加具体的特征。实验结果表明,利用该模型进行影评分析的效果明显好于其它几种模型。

关键词: 影评, 情感分析, 卷积神经网络, 序列标注层, 字粒度词向量

Abstract:

Considering the inherent characteristics of the film review context information and the irrationality of the word order, a CRCNN (Conditional Random Field Convolutional Neural Networks) model is proposed for text sentiment analysis. In order to reduce the impact of noise data on the analysis, the convolutional neural network is improved, and a weight distribution layer is introduced between the input layer and the convolutional layer to analyze the important parts, reduce the noise, and improve the processing characteristics. Using the gradient descent method in the convolutional layer to solve the training parameters will cause the gradient to spread or explode. In order to solve this problem, a gating mechanism is introduced. Finally, the sequence label layer is introduced, and the semantic features of neural network learning are optimized. In addition, the word granularity word vector is used as the feature, which solves the segmentation of the ambiguous word while learning more specific features. Experiments show that the model has significantly better film evaluation effect than other models.

Key words: film review, sentiment analysis, convolutional neural network, sequence labeling layer, word granularity word vector