文献类型：期刊文献

中文题名：基于双层词性感知和多头交互注意机制的方面级情感分析

英文题名：Aspect-level sentiment analysis based on double-layer part-of-speech-aware and multi-head interactive attention mechanism

作者：薛芳[1];过弋[1,2,3];李智强[1];王家辉[1]

机构：[1]华东理工大学信息科学与工程学院,上海200237;[2]大数据流通与交易技术国家工程实验室—商业智能与可视化技术研究中心,上海200436;[3]上海大数据与互联网受众工程技术研究中心,上海200072

年份：2022

卷号：39

期号：3

起止页码：704

中文期刊名：计算机应用研究

外文期刊名：Application Research of Computers

收录：CSTPCD;;北大核心:【北大核心2020】；CSCD:【CSCD_E2021_2022】；

基金：国家重点研发计划资助项目(2018YFC0807105)。

语种：中文

中文关键词：BERT模型;双层词性感知;交互特征;动态特征融合

外文关键词：BERT model;double-layer part-of-speech-aware;interactive features;dynamic feature fusion

摘要：在方面级情感分析研究中,现有工作往往忽略不同类型词性贡献程度以及局部特征和全局特征的交互作用会影响分类准确率的问题。为此,提出了一种基于双层词性感知和多头交互注意机制的方面级情感分析模型DPMHA。首先,使用BERT预训练模型获取包含上下文信息的词向量;其次,提出了双层词性感知的局部特征提取层,重点关注方面词周围具有重要词性词的特征,降低噪声词的影响;接着,在局部特征和全局特征之间设计了多头交互注意力机制,充分挖掘局部特征和全局特征之间重要的交互特征;最后,提出了动态特征融合层和softmax层获取情感分析的结果。在三个公开数据集上的实验结果表明,与现有的方面级情感分析模型相比,提出的DPMHA模型在restaurant14、laptop14、restaurant15数据集上MF1值分别提升了2.41%、1.24%、2.39%,准确率分别提升了1.34%、0.78%、0.37%。
In aspect-level sentiment analysis research,previous work often ignores the problem that the contribution of different types of parts of speech and the interaction of local and global features affects the classification accuracy.This paper proposed an aspect-level sentiment analysis model DPMHA based on double-layer part-of-speech-aware and multi-head interactive attention mechanism.Firstly,this paper used BERT pre-training model to obtain word vectors of contextual information.Secondly,this paper creatively proposed two part-of-speech-aware local feature extraction layers,which could focus on these words around aspect words with important parts of speech and reduce the influence of noise words.Then,this paper designed a multi-head interactive attention mechanism between local features and global features to fully explore the important interactive features between them.Finally,this paper also proposed a dynamic feature fusion layer and softmax layer to obtain the results of sentiment analysis.Experiments on three public data set show that compared with the existing aspect-level sentiment analysis model,the DPMHA model increases the MF1 value of the restaurant14,laptop14,and restaurant15 datasets by 2.41%,1.24%and 2.39%respectively,and the accuracy rate increases by 1.34%,0.78%and 0.37%respectively.