Aspect-Level Sentiment Classification Based on Mixed Graph Neural Network

doi:10.3778/j.issn.1002-8331.2109-0172

Abstract

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）

TANG Hengliang, YIN Qizheng, CHANG Liangliang, XUE Fei, CAO Yang. Aspect-Level Sentiment Classification Based on Mixed Graph Neural Network[J]. Computer Engineering and Applications, 2023, 59(4): 175-182.

唐恒亮, 尹棋正, 常亮亮, 薛菲, 曹阳. 基于混合图神经网络的方面级情感分类[J]. 计算机工程与应用, 2023, 59(4): 175-182.

References

[1] BAKSHI R K，KAUR N，KAUR R，et al.Opinion mining and sentiment analysis[C]//2016 3rd International Conference on Computing for Sustainable Global Development，2016：452-455.
[2] PONTIKI M，GALANIS D，PAVLOPOULOS J，et al.SemEval-2014 task 4：aspect based sentiment analysis[C]//Proceedings of the 8th International Workshop on Semantic Evaluation，2014：27-35.
[3] DONG L，WEI F，TAN C，et al.Adaptive recursive neural network for target-dependent Twitter sentiment classification[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics（Volume 2：Short Papers），2014：49-54.
[4] TANG D，QIN B，FENG X，et al.Effective LSTMs for target-dependent sentiment classification[J].arXiv：1512.01100，2015.
[5] WANG Y，HUANG M，ZHU X，et al.Attention-based LSTM for aspect-level sentiment classification[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing，2016：606-615.
[6] XUE W，LI T.Aspect based sentiment analysis with gated convolutional networks[J].arXiv：1805.07043，2018.
[7] TANG D，QIN B，LIU T.Aspect level sentiment classification with deep memory network[J].arXiv：1605.08900，2016.
[8] CHEN P，SUN Z，BING L，et al.Recurrent attention network on memory for aspect sentiment analysis[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing，2017：452-461.
[9] ZHANG C，LI Q，SONG D.Aspect-based sentiment classification with aspect-specific graph convolutional networks[J].arXiv：1909.03477，2019.
[10] 徐冰冰，岑科廷，黄俊杰，等.图卷积神经网络综述[J].计算机学报，2020，43（5）：755-780.
XU B B，CEN K T，HUANG J J，et al.Summarization of graph integral neural network[J].Chinese Journal of Computers，2020，43（5）：755-780.
[11] TANG H，JI D，LI C，et al.Dependency graph enhanced dual-transformer structure for aspect-based sentiment classification[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics，2020：6578-6588.
[12] HUANG B，CARLEY K M.Syntax-aware aspect level sentiment classification with graph attention networks[J].arXiv：1909.02606，2019.
[13] PONTIKI M，GALANIS D，PAPAGEORGIOU H，et al.SemEval-2015 task 12：aspect based sentiment analysis[C]//Proceedings of the 9th International Workshop on Semantic Evaluation，2015：486-495.
[14] PONTIKI M，GALANIS D，PAPAGEORGIOU H，et al.SemEval2016 task 5：aspect based sentiment analysis[C]//Proceedings of the 10th International Workshop on Semantic Evaluation，2016.
[15] PENNINGTON J，SOCHER R，MANNING C D.GloVe：global vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing，2014：1532-1543.
[16] DEVLIN J，CHANG M W，LEE K，et al.BERT：pre-training of deep bidirectional transformers for language understanding[J].arXiv：1810.04805，2018.
[17] KIRITCHENKO S，ZHU X，CHERRY C，et al.NRC-Canada-2014：detecting aspects and sentiment in customer reviews[C]//Proceedings of the 8th International Workshop on Semantic Evaluation，2014：437-442.
[18] MA D，LI S，ZHANG X，et al.Interactive attention networks for aspect-level sentiment classification[J].arXiv：1709.00893，
2017.
[19] HUANG B，OU Y，CARLEY K M.Aspect level sentiment classification with attention-over-attention neural networks[C]//International Conference on Social Computing，Behavioral-Cultural Modeling and Prediction and Behavior Representation in Modeling and Simulation.Cham：Springer，2018：197-206.
[20] SONG Y，WANG J，JIANG T，et al.Attentional encoder network for targeted sentiment classification[J].arXiv：1902.
09314，2019.
[21] HE R，LEE W S，NG H T，et al.Effective attention modeling for aspect-level sentiment classification[C]//Proceedings of the 27th International Conference on Computational Linguistics，2018：1121-1131.