摘要
特定目标情感分析的目的是从不同目标词语的角度来预测文本的情感,关键是为给定的目标分配适当的情感词。当句子中出现多个情感词描述多个目标情感的情况时,可能会导致情感词和目标之间的不匹配。由此提出了一个CRT机制混合神经网络用于特定目标情感分析,模型使用CNN层从经过BiLSTM变换后的单词表示中提取特征,通过CRT组件生成单词的特定目标表示并保存来自BiLSTM层的原始上下文信息。在三种公开数据集上进行了实验,结果表明,该模型在特定目标情感分析任务中较之前的情感分析模型在准确率和稳定性上有着明显的提升,证明CRT机制能很好地整合CNN和LSTM的优势,这对于特定目标情感分析任务具有重要的意义。
The purpose of target-specific affective analysis is to predict the sentiment of a text from the perspective of different target words.The key is to assign appropriate affective words to a given target.When there are more than one affective word describing multiple target sentiments in a sentence,it may lead to the mismatch between the affective word and the target.This paper proposed a hybrid neural network based on CRT mechanism for target-specific sentiment analysis.The model used CNN layer to extract features from the word representation after BiLSTM transformation.It generated the specific target representation of the word by CRT component and saved the original context information from BiLSTM layer.Experiments on three open datasets show that the proposed model can significantly improve the accuracy and stability of target-specific affective analysis tasks compared with previous models.It is proved that the CRT mechanism can integrate the advantages of CNN and LSTM well,which is of great significance to the task of sentiment analysis for specific targets.
作者
孟威
尉永清
刘文锋
Meng Wei;Wei Yongqing;Liu Wenfeng(School of Information Science&Engineering,Shandong Normal University,Jinan 250014,China;Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology,Shandong Normal University,Jinan 250014,China;Basic Education Dept.,Shandong Police College,Jinan 250014,China;School of Computer Science,Heze University,Heze Shandong 274015,China)
出处
《计算机应用研究》
CSCD
北大核心
2020年第2期360-364,共5页
Application Research of Computers
基金
国家自然科学基金资助项目(61373148)
国家自然科学基金青年基金资助项目(61502151)
山东省社科规划项目(17CHLJ18,17CHLJ33,17CHLJ30)
山东省自然科学基金资助项目(ZR2014FL010)
山东省教育厅基金资助项目(J15LN34).
关键词
特定目标情感分析
自然语言处理
深度学习
卷积神经网络
长短时记忆网络
target-specific sentiment analysis
natural language processing
deep learning
convolutional neural network(CNN)
long short-term memory network(LSTM)