计算机工程与应用 ›› 2018, Vol. 54 ›› Issue (22): 133-138.DOI: 10.3778/j.issn.1002-8331.1801-0163

• 模式识别与人工智能 • 上一篇    下一篇

卷积神经网络在短文本情感多分类标注应用

周锦峰,叶施仁,王  晖   

  1. 常州大学 信息科学与工程学院,江苏 常州 213164
  • 出版日期:2018-11-15 发布日期:2018-11-13

Application of convolutional neural network in multi-category classification for short text sentiment

ZHOU Jinfeng, YE Shiren, WANG Hui   

  1. School of Information Science and Engineering, Changzhou University, Changzhou, Jiangsu 213164, China
  • Online:2018-11-15 Published:2018-11-13

摘要: 情感多分类标注对文本信息的敏感性远高于二分类问题。为了有效利用语义依赖距离和语义多层次进行情感多分类,提出一种多窗口多池化层的卷积神经网络模型。首先使用多窗口的卷积层提取上下文局部语义,然后通过多池化层降低特征维度,同时保留不同层次的语义,由多层次语义构成文本特征向量,最后送入全连接层完成多分类标注。采用斯坦福情感树库数据集验证所提模型的多分类标注效果。实验结果表明,在训练集含短语和未包含短语两种设定下,模型的短文本情感多分类正确率分别达到54.6%和43.5%。

关键词: 情感分析, 多分类标注, 卷积神经网络, 深度学习

Abstract: Deep learning based approaches achieved less for sentiment classification with multiple labels. For this issue, this paper proposes a model called mwmpCNN(multi-windows and multi-pooling Convolutional Neural Network) to grasp the semantic distance and various emotional levels. mwmpCNN assemblies convolution layer with multiple windows to extract local context semantic, and then applies multi-pooling layer to keep multi-level semantic in short text when the feature dimension is reduced. Here, the text feature vector is constructed and reflected by the multi-level semantic, and connection layer is implemented for multi-label classification. This paper evaluates mwmpCNN by the test on Stanford Sentiment Treebank. mwmpCNN exhibits the classification accuracy of 54.6% and 43.5% respectively for the multi-label classification task.

Key words: sentiment analysis, multi-category classification, convolutional neural network, deep learning