Computer Engineering and Applications ›› 2023, Vol. 59 ›› Issue (4): 175-182.DOI: 10.3778/j.issn.1002-8331.2109-0172

• Pattern Recognition and Artificial Intelligence • Previous Articles     Next Articles

Aspect-Level Sentiment Classification Based on Mixed Graph Neural Network

TANG Hengliang, YIN Qizheng, CHANG Liangliang, XUE Fei, CAO Yang   

  1. School of Information, Beijing Wuzi University, Beijing 101149, China
  • Online:2023-02-15 Published:2023-02-15

基于混合图神经网络的方面级情感分类

唐恒亮,尹棋正,常亮亮,薛菲,曹阳   

  1. 北京物资学院 信息学院,北京 101149

Abstract: At present, in aspect-level sentiment analysis research, graph convolutional networks are applied to construct the dependency relationship between aspect words and context words on syntactic dependency trees. However, this improvement is limited due to the instability of syntactic dependency trees and the complexity and irregular expression of sentences. In order to solve the above problems, a neural network model based on mixed graph is proposed. In this model, a multi-layer chart convolutional network applied to the syntactic dependency tree is designed to deeply extract the dependency relationship between aspect words and context words. At the same time, to remove word-level dependency features, a graph attention network with residual connections (Res-GAT) is designed. The main idea is to use word-level dependency features as a supplement, combined with syntactic dependency for aspect-level sentiment classification. Experiments on five classic datasets prove that the model has better classification ability than the baseline model.

Key words: aspect-level sentiment classification, syntactic dependency tree, graph convolutional networks(GCN), graph attention network(GAT)

摘要: 目前在方面级情感分类研究中,图卷积网络被应用于句法依赖树上构建方面词与上下文词的依赖关系。但是由于句法依赖树的不稳定性和语句的复杂性与不规范表达,这种改进较为有限。为解决上述问题,提出了一种基于混合图神经网络模型。在该模型中,为了深度提取方面词与上下文词的依赖关系,设计了应用于句法依赖树的多层图卷积网络。同时为提取词级依赖特征,设计了具有残差连接的图注意力网络(Res-GAT),其主要思想为以词级依赖关系特征作为补充,结合句法依赖关系进行方面级情感分类。通过在五个经典数据集上实验,证明了该模型相较于基线模型具有更优异的分类能力。

关键词: 方面级情感分类, 句法依赖树, 图卷积网络(GCN), 图注意力网络(GAT)