《计算机应用研究》|Application Research of Computers

基于卷积神经网络和Tree-LSTM的微博情感分析

Sentiment analysis of micro-blog based on CNN and Tree-LSTM

免费全文下载 (已被下载 次)  
获取PDF全文
作者 王文凯,王黎明,柴玉梅
机构 郑州大学 信息工程学院,郑州 450001
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2019)05-019-1371-05
DOI 10.19734/j.issn.1001-3695.2017.11.0735
摘要 微博情感分析旨在研究用户关于热点事件的情感观点,研究表明深度学习在微博情感分析上具有可行性。针对传统卷积神经网络进行微博情感分析时忽略了非连续词之间的相关性,为此将注意力机制应用到卷积神经网络(CNN)模型的输入端以改善此问题。由于中文微博属于短文本范畴,卷积神经网络前向传播过程中池化层特征选择存在丢失过多语义特征的可能性,为此在卷积神经网络的输出端融入树型的长短期记忆神经网络(LSTM),通过添加句子结构特征加强深层语义学习。在两种改进基础上构造出一种微博情感分析模型(Att-CTL),实验表明该模型在微博情感分析上具有优良的特性,尤其在极性转移方面仍保持较高的F1值。
关键词 卷积神经网络; 注意力机制; 长短期记忆神经网络; 微博情感分析
基金项目 社会媒体文本情感可视计算方法研究基金资助项目(U1636111)
本文URL http://www.arocmag.com/article/01-2019-05-019.html
英文标题 Sentiment analysis of micro-blog based on CNN and Tree-LSTM
作者英文名 Wang Wenkai, Wang Liming, Chai Yumei
机构英文名 School of Information Engineering,Zhengzhou University,Zhengzhou 450001,China
英文摘要 Micro-blog sentiment analysis aims to study the emotional views of users on hot events, and research shows that deep learning is feasible in micro-blog's sentiment analysis. In view of traditional convolutional neural network, micro-blog sentiment analysis ignores the correlation between discontinuous words. Therefore, this paper applied attention mechanism to the input end of convolutional neural network(CNN) model to improve this problem. Because Chinese micro-blog belongs to the short text category, there was a possibility of losing too many semantic features in the selection of pooling layer features in the process of convolutional neural network forward propagation, so into the long short term memory neural network tree at the output of the convolutional neural network terminal(LSTM), by adding the sentence structure to strengthen the deep semantic learning. Based on the two improvements, it constructed a Chinese micro-blog sentiment analysis model(Att-CTL). Experiments show that the model has excellent characteristics in Chinese micro-blog sentiment analysis, especially in polarity shifting, and maintains a high F1 value.
英文关键词 CNN; attention mechanism; LSTM; micro-blog sentiment analysis
参考文献 查看稿件参考文献
 
收稿日期 2017/11/5
修回日期 2017/12/27
页码 1371-1375
中图分类号 TP391
文献标志码 A