融合词性与外部知识的方面级情感分析

doi:10.3778/j.issn.1673-9418.2207077

摘要/Abstract

摘要： 方面级情感分析的目标是识别给定句子中特定方面词的情感极性，目前结合图卷积神经网络和句法依存树的大部分研究侧重于根据句子依赖树学习上下文和方面词间的关系，而没有专注于句法依赖树的构建，从而不能充分地利用依赖树上的信息，并且会引入噪声。针对上述问题，提出一种基于多融合邻接矩阵算法的图卷积网络模型。首先使用外部知识来增强句子中情感词的作用，并利用词性进行信息筛选，去除句子中冗余的依赖关系从而得到剪枝句法依赖树，使用多融合邻接矩阵算法将两者结合得到句法信息，将句法信息和BiLSTM层提取的语义信息输入到简化图卷积网络中进行特征融合。在五个数据集上的实验结果表明，提出的改进方法是有效的，且能明显提高模型性能。

关键词: 方面级情感分析, 图卷积神经网络（GCN）, 外部知识, 词性, 句法依赖树

Abstract: The goal of aspect level affective analysis is to identify the affective polarity of specific aspect words in a given sentence. At present, most of the research combining graph convolution neural network and syntactic dependency tree focuses on learning the relationship between context and aspect words according to the sentence dependency tree, but does not focus on the construction of syntactic dependency tree, so it can’t make full use of the information on the dependency tree, and will introduce noise. To solve the above problems, this paper proposes a graph convolution network model based on multi-fusion adjacency matrix algorithm. Firstly, external knowledge is used to enhance the role of emotional words in sentences, and the part-of-speech is used for information filtering to remove redundant dependencies in sentences to obtain pruned syntactic dependency trees. The two are combined by multi-fusion adjacency matrix algorithm to obtain syntactic information. The syntactic information and the semantic information extracted from the BiLSTM layer are input into the simplified graph convolution network for feature fusion. Experimental results on five datasets show that the proposed method is effective and can significantly improve the performance of the model.

Key words: aspect sentiment analysis, graph convolutional network (GCN), external knowledge, part-of-speech;syntactic dependency tree

谷雨影, 高美凤. 融合词性与外部知识的方面级情感分析[J]. 计算机科学与探索, 2023, 17(10): 2488-2498.

GU Yuying, GAO Meifeng. Aspect-Level Sentiment Analysis Combining Part-of-Speech and External Knowledge[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(10): 2488-2498.

参考文献

[1] MALOUF R, MULLEN T. Taking sides: user classification for informal online political discourse[J]. Internet Research, 2008, 18(2): 177-190.
[2] KIM Y. Convolutional neural networks for sentence classifi-cation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Oct 25-29, 2014. Stroudsburg: ACL, 2014: 1746-1751.
[3] MNIH V, HEESS N, GRAVES A, et al. Recurrent models of visual attention[C]//Advances in Neural Information Processing?Systems?27, Montreal, Dec?8-13,?2014: 2204-2212.
[4] BAHDANAU D, CHO K, BENGIO Y. Neural machine trans-lation by jointly learning to align and translate[J]. arXiv:1409.0473, 2014.
[5] ZHOU J, JIN S Q, HUANG X L. ADeCNN: an improved model for aspect-level sentiment analysis based on defor-mable CNN and attention[J]. IEEE Access, 2020, 8: 132970-132979.
[6] LIN P Q, TANG M, LAI J H. Deep selective memory network with selective attention and inter-aspect modeling for aspect level sentiment classification[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021, 29: 1093-1106.
[7] FAN F F, FENG Y S, ZHAO D Y. Multi-grained attention network for aspect-level sentiment classification[C]//Proc-eedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Oct 31-Nov 4, 2018. Stroudsburg: ACL, 2018: 3433-3442.
[8] WU C, XIONG Q Y, YANG Z Y, et al. Residual attention and other aspects module for aspect-based sentiment anal-ysis[J]. Neurocomputing, 2021, 435: 42-52.
[9] 韩虎, 郝俊, 张千锟, 等. 知识增强的交互注意力方面级情感分析模型[J]. 计算机科学与探索, 2023, 17(3): 709-718. HAN H, HAO J, ZHANG Q K, et al. Knowledge-enhanced interactive attention model for aspect-based sentiment anal-ysis[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(3): 709-718.
[10] 孙佳慧, 韩萍, 程争. 基于知识迁移和注意力融合的方面级文本情感分析[J]. 信号处理, 2021, 37(8): 1384-1391.
SUN J H, HAN P, CHENG Z. Aspect-level sentiment anal-ysis based on knowledge transfer and attention fusion[J]. Journal of Signal Processing, 2021, 37(8): 1384-1391.
[11] REN Z Y, ZENG G P, LIU C, et al. A lexicon-enhanced attention network for aspect-level sentiment analysis[J]. IEEE Access, 2020, 8: 93464-93471.
[12] VALLE-CRUZ D, FERNANDEZ-CORTEZ V, LóPEZ-CHAU A, et al. Does twitter affect stock market decisions? Financial sentiment analysis during pandemics: a comp-arative study of the H1N1 and the COVID-19 periods[J]. Cognitive Computation, 2022, 14(1): 372-387.
[13] DISTANTE D, FARALLI S, RITTINGHAUS S, et al. Dom-ainSenticNet: an ontology and a methodology enabling domain-aware sentic computing[J]. Cognitive Computation, 2022, 14(1): 62-77.
[14] MA Y K, PENG H Y, CAMBRIA E. Targeted aspect-based sentiment analysis via embedding commonsense knowl-edge into an attentive LSTM[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence, the 30th Innovative Applications of Artificial Intelligence, and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence, New Orleans, Feb 2-7, 2018. Menlo Park: AAAI, 2018: 5876-5883.
[15] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[C]//Proceedings of the 5th International Conference on Learning Representations, Toulon, Apr 24-26, 2017: 1-14.
[16] 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 Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, Hong Kong, China, Nov 3-7, 2019. New York: ACM, 2019: 4567-4577.
[17] WANG B, GUO P F, WANG X, et al. Transparent aspect-level sentiment analysis based on dependency syntax anal-ysis and its application on COVID-19[J]. ACM Journal of Data and Information Quality, 2022, 14(2): 1-24.
[18] YU B G, ZHANG S W. A novel weight-oriented graph convolutional network for aspect-based sentiment analysis[J]. The Journal of Supercomputing, 2023, 79(1): 947-972.
[19] XU K H, ZHAO H, LIU T W. Aspect-specific hetero-geneous graph convolutional network for aspect-based sent-iment classification[J]. IEEE Access, 2020: 139346-139355.
[20] ZHAO M, YANG J, ZHANG J P, et al. Aggregated graph convolutional networks for aspect-based sentiment classif-ication[J]. Information Sciences, 2022, 600: 73-93.
[21] XU G T, LIU P Y, ZHU Z F, et al. Attention-enhanced graph convolutional networks for aspect-based sentiment classification with multi-head attention[J]. Applied Sciences, 2021, 11(8): 3640.
[22] LI X W, LU R, LIU P Y, et al. Graph convolutional networks with hierarchical multi-head attention for aspect-level sentiment classification[J]. The Journal of Super-computing, 2022, 78(13): 14846-14865.
[23] FELIX W, ZHANG T Y, AHD S, et al. Simplifying graph convolutional networks[J]. arXiv:1902.07153, 2019.
[24] LIANG B, SU H, GUI L, et al. Aspect-based sentiment analysis via affective knowledge enhanced graph convo-lutional networks[J]. Knowledge-Based Systems, 2022, 235: 107643.
[25] XIAO L W, XUE Y, WANG H, et al. Exploring fine-grained syntactic information for aspect-based sentiment classifi-cation with dual graph neural networks[J]. Neurocomputing, 2022, 471: 48-59.
[26] LI D, WEI F R, TAN C Q, 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, Baltimore, Jun 23-25, 2014. Stroudsburg: ACL, 2014: 49-54.
[27] PONTIKI M, GALANIS D, PAYlLOPOULOS J, et al. SemEval-2014 task 4: aspect based sentiment analysis[C]//Proceedings of the 8th International Workshop on Semantic Evaluation, Dublin, Aug 23-24, 2014. Stroudsburg: ACL, 2014: 27-35.
[28] 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, Denver, Jun 4-5, 2015. Stroudsburg: ACL, 2015: 486-495.
[29] PONTIKI M, GALANIS D, PAPAGEORGIOU H, et al. SemEval-2016 task 5: aspect based sentiment analysis[C]//Proceedings of the 10th International Workshop on Semantic Evaluation, San Diego, Jun 16-17, 2016. Stroudsburg: ACL, 2016: 19-30.
[30] KIRITCHENKO S, ZHU X D, CHERRY C, et al. Detecting aspects and sentiment in customer reviews[C]//Proc-eedings of the 8th International Workshop on Semantic Evaluation, Dublin, Aug 23-24, 2014. Stroudsburg: ACL, 2014: 437-442.
[31] TANG D Y, QIN B, FENG X C. Effective LSTMs for target-dependent sentiment classification[C]//Proceedings of the 26th International Conference on Computational Linguistics, Osaka, Dec 11-16, 2016. Stroudsburg: ACL, 2016: 3298-3307.
[32] TANG D Y, QIN B, FENG X C, et al. Aspect level senti-ment classification with deep memory network[C]//Proce-edings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, Nov 1-4, 2016. Strou-dsburg: ACL, 2016: 214-224.
[33] MA D H, LI S J, ZHANG X D, et al. Interactive attention networks for aspect-level sentiment classification[C]//Proc-eedings of the 26th International Joint Conference on Artificial Intelligence, Melbourne, Aug 19-25, 2017: 4068-4074.
[34] SONG Y W, WANG J H, JIANG T, et al. Attentional encoder network for targeted sentiment classification[C]//Proceedings of the 28th International Conference on Arti-ficial Neural Networks and Machine Learning， Munich, Sep 17-19, 2019. Cham: Springer, 2019: 93-103.
[35] CHEN Z, QIAN T Y. Transfer capsule network for aspect level sentiment classification[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Ling-uistics, Florence, Jul 28-Aug 2, 2019. Stroudsburg: ACL, 2019: 547-556.
[36] HUANG B X, KATHLEEN M C. Aspect level sentiment classification with attention-over-attention neural networks[C]//LNCS 10899：Proceedings of the 2018 International Conference on Social Computing, Behavioral-Cultural Mod-eling and Prediction and Behavior Representation in Mode-ling and Simulation, Washington, Jul 10-13, 2018. Cham: Springer, 2018: 197-206.
[37] SUN K, ZHANG R C, MENSAH S, et al. Aspect-level sentiment 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 Proce-ssing, Hong Kong, China, Nov 3-7, 2019. Stroudsburg: ACL, 2019: 5678-5687.
[38] HUANG B X, KATHLEEN M C. Syntax-aware aspect level sentiment classification with graph attention networks[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Proce-ssing, Hong Kong, China, Nov 3-7, 2019. Stroudsburg: ACL, 2019: 5469-5477.