基于BERT模型和图注意力网络的方面级情感分析  

Aspect-based Sentiment Analysis Based on BERT Model and Graph Attention Network

作　　者：林煌 李弼程[1] LIN Huang;LI Bicheng(College of Computer Science and Technology,Huaqiao University,Xiamen,Fujian 361021,China)

机构地区：[1]华侨大学计算机科学与技术学院,福建厦门361021

出　　处：《计算机科学》2024年第S02期108-114,共7页Computer Science

基　　金：装备预研教育部联合基金(8091B022150)。

摘　　要：方面级情感分析是一项细粒度的情感分析任务,旨在对给定文本中的特定方面进行情感极性分析。当前基于语法分析的方法严重依赖于依存树的单一解析结果,并且大部分研究对于语义和语法特征的融合并不充分。因此,提出了一种基于BERT模型和图注意力网络的方面级情感分析方法。该方法能够充分挖掘句子结构中的语义和语法信息,并通过交互注意力机制融合这些信息,从而获得更精确的情感特征。首先,利用BERT预训练模型得到文本的初始化向量,并使用注意力机制对方面词进行全局的语义信息关联,得到文本的语义特征。其次,利用语法解析器构建短语结构图和依存图,并利用图注意力网络对节点信息进行编码,得到文本的语法特征。最后,通过交互注意力机制结合学习到的语义和语法特征,实现了多个视角的融合,从而全面理解方面-观点关系。实验结果表明,所提方法在多个数据集上的ACC值和F1值均优于现有的多个先进方法。Aspect-based sentiment analysis is a fine-grained sentiment analysis task that aims to analyze the sentiment polarity of specific aspects in a given text.Current syntax-based methods heavily rely on a single parsing result from the dependency tree,and most of the existing research lacks sufficient integration of semantic and syntactic features.Therefore,this paper proposes an aspect-based sentiment analysis approach based on the BERT model and graph attention network.This method can effectively explo the semantic and syntactic information in sentence structures and fuse these information through an interactive attention mechanism to obtain more accurate sentiment features.Firstly,the BERT pre-trained model is utilized to obtain the initial vectors of the text,and an attention mechanism is employed to associate the globalsemantic information of aspect words,resulting in the semantic features of the text.Secondly,a syntax parser is used to construct a phrase structure graph and a dependency graph,and a graph attention network is applied to encode the node information,leading to the syntactic features of the text.Finally,through an interactive attention mechanism,the learned semantic and syntactic features are combined to achieve a comprehensive understanding of aspect-opinion relationships from multiple perspectives.Experimental results show that the proposed method outperforms the existing state-of-the-art methods with ACC and F1 values on multiple datasets.

关 键 词：方面级情感分析 语法分析 图注意力网络 注意力机制 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]