计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (12): 262-269.doi: 10.11896/jsjkx.221000090

• 人工智能 • 上一篇    下一篇

融合句法距离与方面注意力的方面级情感分析

张隆基1, 赵晖2   

  1. 1 新疆大学软件学院 乌鲁木齐 830000
    2 新疆大学信息科学与工程学院 乌鲁木齐 830000
  • 收稿日期:2022-10-12 修回日期:2023-03-15 出版日期:2023-12-15 发布日期:2023-12-07
  • 通讯作者: 赵晖(zhaohui@xju.edu.cn)
  • 作者简介:(13009626824@163.com)
  • 基金资助:
    国家自然科学基金(62166041)

Aspect-level Sentiment Analysis Integrating Syntactic Distance and Aspect-attention

ZHANG Longji1, ZHAO Hui2   

  1. 1 College of Software,Xinjiang University,Urumqi 830000,China
    2 School of Information Science and Engineering,Xinjiang University,Urumqi 830000,China
  • Received:2022-10-12 Revised:2023-03-15 Online:2023-12-15 Published:2023-12-07
  • About author:ZHANG Longji,born in 1996,postgra-duate.His main research interests include natural language processing,aspect based sentiment analysis,etc.
    ZHAO Hui,born in 1972,Ph.D,professor,Ph.D supervisor,is a member of China Computer Federation.Her main research interests include artificial intelligence,affective computing,speech and digital image processing.
  • Supported by:
    National Natural Science Foundation of China(62166041).

PDF (PC)

2412

摘要： 目前,基于句法依存树的图卷积网络面临着卷积层数过深而产生过平滑的问题,无法提取句法依存树的全局节点信息。虽然搭配序列模型可以提取到语句的上下文的信息,但是序列模型依赖时序的特点导致图卷积网络无法有效地区分上下文特征对方面项的贡献度。针对上述问题,提出了一种基于句法距离和方面关注注意力机制的新型图卷积网络模型。首先,该模型利用双向长短期记忆网络分别学习语句和方面项的上下文信息,同时结合图卷积网络学习语句的句法依存信息。其次,依据句法依存树计算所有节点之间的句法依存距离,设定阈值削弱长距离特征的权重占比,提高图卷积模型区分上下文特征的能力。最后,设计具有残差连接的注意力机制,指导方面项自动聚焦于语句中的重要信息。实验结果表明,相较于基线方法,所提模型在多个公开数据集上展现出了较好的分析性能,在Twitter数据集和Laptop数据集上的情感分类准确率分别高达75.94%和78.59%,表明了所提方法的有效性。

关键词: 图卷积网络, 句法依存树, 句法依存距离, 注意力机制, 方面级情感分析

Abstract: Currently,the over-smoothing problem arises from deep convolution in syntactic dependency tree-based graph convolutional networks.This problem prevents the convolutional graph network from extracting the global node information of the syntactic dependency tree.Although the sequential model can extract information about the context of the sentence,the timing-dependent nature of the sequential model leads to the inability of the graph convolutional network to effectively distinguish the contribution of context features to aspect terms.This paper proposes a novel graph convolutional network model based on syntactic distance and aspect focus attention mechanisms to address the above problems.First,the model learns the contextual information of sentences and aspect terms separately using a bidirectional long short-term memory network and uses a convolutional graph network to learn the syntactic dependency information of sentences.Secondly,this model calculates the syntactic dependency distance among all nodes based on the syntactic dependency tree,sets a threshold to weaken the weight share of long-distance features,and improves the ability of the graph convolution model to distinguish context features.Finally,this paper also designs attention mechanisms with residual connectivity to automatically guide the aspect terms to focus on the critical information in the sentence.Experimental results demonstrate that the model exhibits better analytical performance on several publicly available datasets compared to the baseline approach,with sentiment classification accuracy as high as 75.94% and 78.59% on the Twitter and Laptop datasets,demonstrating the effectiveness of the proposed approach.

Key words: Graph convolutional networks, Syntactic dependency tree, Syntactic dependency distances, Attention mechanisms, Aspect-level sentiment analysis

中图分类号: 

  • TP391
[1]DONTHU N,KUMAR S,PANDEY N,et al.Mapping the electronic word-of-mouth(eWOM) research:A systematic review and bibliometric analysis[J].Journal of Business Research,2021,135:758-773.
[2]DANDREA E,DUCANGE P,BECHINI A,et al.Monitoringthe public opinion about the vaccination topic from tweets ana-lysis[J].Expert Systems with Applications,2019,116:209-226.
[3]KULKARNI K,KALRO A D,SHARMA D,et al.A typology of viral ad sharers using sentiment analysis[J].Journal of Retailing and Consumer Services,2020,53:101739.
[4]MEDSKER L R,JAIN L C.Recurrent neural networks[J].Design and Applications,2001,5:64-67.
[5]GRAVES A,MOHAMED A,HINTON G.Speech recognitionwith deep recurrent neural networks[C]//2013 IEEE International Conference on Acoustics,Speech and Signal Processing.IEEE,2013:6645-6649.
[6]DEY R,SALEM F M.Gate-variants of gated recurrent unit(GRU) neural networks[C]//2017 IEEE 60th International Midwest Symposium on Circuits and Systems(MWSCAS).IEEE,2017:1597-1600.
[7]HE R D,LEE W S,NG H T,et al.Effective Attention Modeling for Aspect-Level Sentiment Classification[C]//International Conference on Computational Linguistics.Association for Computational Linguistics,2018:1121-1131.
[8]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[J].arXiv:1609.02907,2016.
[9]ZHANG Y H,QI P,MANNING C D.Graph convolution overpruned dependency trees improves relation extraction[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.2018:2205-2215.
[10]VELIČKOVIĆ P,CUCURULL G,CASANOVA A,et al.Graph attention networks[J].arXiv:1710.10903,2017.
[11]HAN H,WU Y H,QIN X Y.An interaction graph attentionnetworks model for aspect-level sentiment analysis[J].Journal of Electronics and Information,2021,43(11):3282-3290.
[12]WU H S,MIAO Y Q,ZHANG W Z,et al.Aspect level sentiment analysis based on distance and graph convolution network[J].Journal of Application Research of Computers,2021,38(11):3274-3278.
[13]TANG D Y,QIN B,FENG X,et al.Effective LSTMs for target-dependent sentiment classification[J].arXiv:1512.01100,2015.
[14]WANG Y Q,HUANG M L,ZHU X Y,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.
[15]MA D H,LI S J,ZHANG X D,et al.Interactive attention networks for aspect-level sentiment classification[J].arXiv:1709.00893,2017.
[16]CHEN P,SUN Z Q,BING L D,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.
[17]FAN F,FENG Y S,ZHAO D Y.Multi-grained attention net-work for aspect-level sentiment classification[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.2018:3433-3442.
[18]XING B W,LIAO L J,SONG D,et al.Earlier attention? aspect-aware LSTM for aspect-based sentiment analysis[J].arXiv:1905.07719,2019.
[19]GU S Q,ZHANG L P,HOU Y X,et al.A position-aware bidirectional attention network for aspect-level sentiment analysis[C]//Proceedings of the 27th International Conference on Computational Linguistics.2018:774-784.
[20]GILMER J,SCHOENHOLZ S,RILEY P F,et al.Message pas-sing neural networks[M]//Machine Learning Meets Quantum Physics.Cham:Springer,2020:199-214.
[21]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 Confe-rence on Natural Language Processing(EMNLP-IJCNLP).2019:5679-5688.
[22]ZHANG C,LI Q C,SONG D W.Aspect-based sentiment classification with aspect-specific graph convolutional networks[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJCNLP).2019:4568-4578.
[23]LU Q,ZHU Z F,ZHANG G Y,et al.Aspect-gated graph convolutional networks for aspect-based sentimentanalysis[J].Applied Intelligence,2021,51(7):4408-4419.
[24]CHEN J P,HUANG Z H,XUE Y.Bilateral-brain-like Semantic and Syntactic Cognitive Network for Aspect-level Sentiment Analysis[C]//2021 International Joint Conference on Neural Networks(IJCNN).IEEE,2021:1-8.
[25]CHEN C H,TENG Z Y,ZHANG Y.Inducing target-specific latent structures for aspect sentiment classification[C]//Procee-dings of the 2020 Conference on Empirical Methods in Natural Language Processing(EMNLP).2020:5596-5607.
[26]ZHANG M,QIAN T Y.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(EMNLP).2020:3540-3549.
[27]PANG S G,XUE Y,YAN Z H,et al.Dynamic and multi-channel graph convolutional networks for aspect-based sentiment analysis[C]//Findings of the Association for Computational Linguistics:ACL-IJCNLP 2021.2021:2627-2636.
[28]LI R F,CHEN H,FENG F X,et al.Dual graph convolutional networks for aspect-based sentiment analysis[C]//Proceedings of the 59th Annual Meeting of the Association for Computa-tional Linguistics and the 11th International Joint Conference on Natural Language Processing(Volume 1:Long Papers).2021:6319-6329.
[29]LI D,WEI F R,TAN C Q,et al.Adaptive recursive neural net-work 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.
[30]PONTIKI M,GALANIS D,PAPAGEORGIOU H,et al.Semeval-2016 task 5:Aspect based sentiment analysis[C]//International Workshop on Semantic Evaluation.2016:19-30.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发