用于方面级情感分析的情感增强双图卷积网络

doi:10.3778/j.issn.1673-9418.2209033

摘要/Abstract

摘要： 方面级情感分析是一项细粒度的情感分类任务。近年来，依存树上的图神经网络被用于建模方面项及其意见项间的依赖关系。然而，这类方法通常具有高度依赖依存树解析质量的缺点。同时，大多数现有研究着重关注语法信息，忽视了情感知识在建模特定方面与上下文之间情感依赖关系中的作用。为解决以上问题，设计并提出了用于方面级情感分析的情感增强双图卷积网络。模型基于依存树与注意力机制建立双通道结构，在更为准确、高效地捕捉方面与上下文间语法与语义关联的同时减轻了模型对依存树的依赖程度。此外，模型引入情感知识用于增强图结构，帮助模型更好地提取特定方面的情感依赖关系。模型在3个公开基准数据集Rest14、Lap14、Twitter上的准确率分别达到了84.32%、78.20%、76.12%，接近或超越目前最先进的性能。实验表明，提出的方法能够合理利用语义和语法信息，在使用更少参数的情况下实现较为先进的情感分类性能。

关键词: 方面级情感分析, 注意力机制, 依存树, 图卷积网络, 情感知识

Abstract: Aspect-based sentiment analysis is a fine-grained sentiment classification task. In recent years, graph neural network on dependency tree has been used to model the dependency relationship between aspect terms and their opinion terms. However, such methods usually have the disadvantage of highly dependent on the quality of dependency parsing. Furthermore, most existing works focus on syntactic information, while ignoring the effect of affective knowledge in modeling the sentiment-related dependencies between specific aspects and context. In order to solve these problems, an affection enhanced dual graph convolution network is designed and proposed for aspect-based sentiment analysis. The model establishes a dual channel structure based on the dependency tree and attention mechanism, which can more accurately and efficiently capture the syntactic and semantic dependencies between aspects and contexts, and reduce the dependence of the model on the dependency tree. In addition, affective knowledge is integrated to enhance the graph structure and help the model better extract the sentiment-related dependencies of specific aspects. The accuracy of the model on the three open benchmark datasets Rest14, Lap14 and Twitter reaches 84.32%, 78.20% and 76.12% respectively, approaching or exceeding the state-of-the-art perfor-mance. Experiments show that the method proposed can make rational use of semantic and syntactic information, and achieves advanced sentiment classification performance with fewer parameters.

Key words: aspect-based sentiment analysis, attention mechanism, dependency tree, graph convolutional networks, affective knowledge

张文轩, 殷雁君, 智敏. 用于方面级情感分析的情感增强双图卷积网络[J]. 计算机科学与探索, 2024, 18(1): 217-230.

ZHANG Wenxuan, YIN Yanjun, ZHI Min. Affection Enhanced Dual Graph Convolution Network for Aspect Based Sentiment Analysis[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(1): 217-230.

参考文献

[1] LIU B. Sentiment analysis and opinion mining[M]//Synthesis Lectures on Human Language Technologies. San Rafael: Morgan & Claypool Publishers, 2012: 1-167.
[2] 张严，李天瑞. 面向评论的方面级情感分析综述[J]. 计算机科学, 2020, 47(6): 194-200.
ZHANG Y, LI T R. Review of comment-oriented aspect-based sentiment analysis[J]. Computer Science, 2020, 47(6): 194-200.
[3] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Proces-sing Systems 30, Long Beach, Dec 4-9, 2017: 5998-6008.
[4] LIU H, CHATTERJEE I, ZHOU M C, et al. Aspect-based sentiment analysis: a survey of deep learning methods[J]. IEEE Transactions on Computational Social Systems, 2020, 7(6): 1358-1375.
[5] ZHANG W, LI X, DENG Y, et al. A survey on aspect-based sentiment analysis: tasks, methods, and challenges[J]. arXiv: 2203.01054, 2022.
[6] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[J]. arXiv:1609.02907, 2016.
[7] VELI?KOVI? P, CUCURULL G, CASANOVA A, et al. Graph attention networks[J]. arXiv:1710.10903, 2017.
[8] LIANG B, SU H, GUI L, et al. Aspect-based sentiment analysis via affective knowledge enhanced graph convolu-tional networks[J]. Knowledge-Based Systems, 2022, 235: 107643.
[9] TANG H, JI D, LI C, et al. Dependency graph enhanced dual-transformer structure for aspect-based sentiment classi-fication[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2020: 6578-6588.
[10] LI R, CHEN H, FENG F, et al. Dual graph convolutional networks for aspect-based sentiment analysis[C]//Proceed-ings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Stroudsburg: ACL, 2021: 6319-6329.
[11] DING X, LIU B, YU P S. A holistic lexicon-based approach to opinion mining[C]//Proceedings of the 2008 International Conference on Web Search and Data Mining. New York:ACM, 2008: 231-240.
[12] 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, Dublin, Aug 23-24, 2014: 437-442.
[13] 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. Stroudsburg: ACL, 2016: 606-615.
[14] MA D, LI S, ZHANG X, et al. Interactive attention networks for aspect-level sentiment classification[J]. arXiv:1709.00893, 2017.
[15] FAN F, FENG Y, ZHAO D. Multi-grained attention network for aspect-level sentiment classification[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2018: 3433-3442.
[16] HUANG B, OU Y, CARLEY K M. Aspect level sentiment classification with attention-over-attention neural networks[C]//Proceedings of the 2018 International Conference on Social Computing, Behavioral-Cultural Modeling and Pred-iction and Behavior Representation in Modeling and Simul-ation. Cham: Springer, 2018: 197-206.
[17] CHEN D, MANNING C D. A fast and accurate dependency parser using neural networks[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2014: 740-750.
[18] ZHANG C, LI Q C, SONG D W. Aspect-based sentiment classification with aspect-specific graph convolutional net-works[C]//Proceedings of the 2019 Conference on Empri-cal Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Proces-sing. Stroudsburg: ACL, 2019: 4568-4578.
[19] HUANG B, CARLEY K M. Syntax-aware aspect level sen-timent classification with graph attention networks[C]//Pro-ceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg: ACL, 2019: 5469-5477.
[20] WANG K, SHEN W, YANG Y, et al. Relational graph attention network for aspect-based sentiment analysis[J]. arXiv:2004.12362, 2020.
[21] XU G, LIU P, ZHU Z, et al. Attention-enhanced graph con-volutional networks for aspect-based sentiment classifica-tion with multi-head attention[J]. Applied Sciences, 2021, 11(8): 3640.
[22] CHEN C, TENG Z, ZHANG Y. Inducing target-specific latent structures for aspect sentiment classification[C]//Pro-ceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2020: 5596-5607.
[23] MA Y, PENG H, CAMBRIA E. Targeted aspect-based senti-ment analysis via embedding commonsense knowledge into an attentive LSTM[C]//Proceedings of the 32nd AAAI Con-ference on Artificial Intelligence and the 30th Innovative Applications of Artificial Intelligence Conference and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence. Menlo Park: AAAI, 2018: 5876-5883.
[24] ZHONG Q, DING L, LIU J, et al. Knowledge graph aug-mented network towards multiview representation learning for aspect-based sentiment analysis[J]. arXiv:2201.04831, 2022.
[25] SUN K, ZHANG R, MENSAH S, et al. Aspect-level senti-ment analysis via convolution over dependency tree[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Strouds-burg: ACL, 2019: 5679-5688.
[26] CAMBRIA E, LI Y, XING F Z, et al. SenticNet 6: ensem-ble application of symbolic and subsymbolic AI for senti-ment analysis[C]//Proceedings of the 29th ACM Internatio-nal Conference on Information & Knowledge Management. New York: ACM, 2020: 105-114.
[27] XING F Z, PALLUCCHINI F, CAMBRIA E. Cognitive-inspired domain adaptation of sentiment lexicons[J]. Infor-mation Processing & Management, 2019, 56(3): 554-564.
[28] 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. Stroudsburg: ACL, 2014: 27-35.
[29] DONG L, WEI F, TAN C, et al. Adaptive recursive neural network for target-dependent Twitter sentiment classifica-tion[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2014: 49-54.
[30] 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. Stroudsburg: ACL, 2014: 1532-1543.
[31] 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 Asso-ciation for Computational Linguistics. Stroudsburg: ACL, 2014: 49-54.
[32] LI X, BING L, LAM W, et al. Transformation networks for target-oriented sentiment classification[J]. arXiv:1805.01086, 2018.
[33] ZHANG M, QIAN T. Convolution over hierarchical syntactic and lexical graphs for aspect level sentiment analysis[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2020: 3540-3549.
[34] PANG S, XUE Y, YAN Z, et al. Dynamic and multi-channel graph convolutional networks for aspect-based sentiment analysis[C]//Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Stroudsburg: ACL, 2021: 2627-2636.