计算机科学 ›› 2023, Vol. 50 ›› Issue (4): 196-203.doi: 10.11896/jsjkx.220100105

• 人工智能 • 上一篇    下一篇

基于交互注意力和图卷积网络的方面级情感分析

王娅丽1, 张凡1,2, 余增1,2, 李天瑞1,2   

  1. 1 西南交通大学计算机与人工智能学院 成都 611756
    2 综合交通大数据应用技术国家工程实验室 成都 611756
  • 收稿日期:2022-01-11 修回日期:2022-09-01 出版日期:2023-04-15 发布日期:2023-04-06
  • 通讯作者: 李天瑞(trli@swjtu.edu.cn)
  • 作者简介:(18398618821@163.com)
  • 基金资助:
    国家自然科学基金(61773324);四川省重点研发项目(2020YFG0035)

Aspect-level Sentiment Classification Based on Interactive Attention and Graph Convolutional Network

WANG Yali1, ZHANG Fan1,2, YU Zeng1,2, LI Tianrui1,2   

  1. 1 School of Computing and Artificial Intelligence,Southwest Jiaotong University,Chengdu 611756,China
    2 National Engineering Laboratory of Integrated Transportation Big Data Application Technology,Chengdu 611756,China
  • Received:2022-01-11 Revised:2022-09-01 Online:2023-04-15 Published:2023-04-06
  • About author:WANG Yali,born in 1997,postgra-duate,is a member of China Computer Federation.Her main research interests include sentiment analysis and natural language processing.
    LI Tianrui,born in 1969,Ph.D,professor,Ph.D supervisor,is a distinguished member of China Computer Federation.His main research interests include big data intelligence,rough sets,granular computing.
  • Supported by:
    National Natural Science Foundation of China(61773324) and Sichuan Key R&D Project(2020YFG0035).

摘要: 方面级情感分析是细粒度情感分析中的一项关键任务,旨在预测一个句子中不同方面术语的情感倾向。针对目前结合图卷积网络的研究忽略方面术语本身的含义以及方面术语与上下文之间的交互的问题,文中提出了基于交互注意力和图卷积网络的模型(Interactive Attention Graph Convolution Network,IAGCN)。该模型首先结合BiLSTM和修正动态权重层对上下文进行建模,其次在句法依存树上使用图卷积网络对句法信息进行编码,然后利用交互注意力机制学习上下文和方面术语中的注意力,重构上下文和方面术语的表示,最后通过softmax层获取给定方面术语的情感极性。与基线模型相比,所提模型在5个数据集中的准确率和F1值分别提高了0.56%~1.75%和1.34%~4.04%。同时,将预训练模型BERT应用到此任务中,相比基于GloVe的IAGCN模型,其准确率和F1值分别提高了1.47%~3.95%和2.59%~7.55%,模型效果有了进一步的提升。

关键词: 方面级情感分析, 深度学习, 图卷积网络, 交互注意力机制, BERT

Abstract: Aspect-level sentiment analysis is a key task in fine-grained sentiment analysis,which aims to predict the sentiment tendency of different aspect terms in a sentence.In view of the fact that the current research combined with graph convolution network ignores the meaning of aspect terms themselves and the interaction between aspect terms and context,an interactive attention graph convolutional network model is proposed,named interactive attention graph convolution network(IAGCN).It firstlycombines BiLSTM and modified dynamic weights to model context.Secondly,the syntactic information is encoded by exploiting graph convolutional network on syntactic dependency tree.Then,the attention among context and aspect terms is investigated through interactive attention mechanism and the representation of context and aspect term is reconstructed.Finally,the sentiment polarity of a given aspect term is obtained through a softmax layer.Compared with the baseline models,the accuracy rate and F1 score of the proposed model improves by 0.56%~1.75% and 1.34%~4.04% on 5 datasets,respectively.At the same time,the pre-training model BERT is applied to this task.Compared with the IAGCN based on GloVe model,its accuracy rate and F1 score increases by 1.47%~3.95% and 2.59%~7.55%,respectively.Thus,the model effect has been further improved.

Key words: Aspect-level sentiment analysis, Deep learning, Graph convolutional network, Interactive attention mechanism, BERT

中图分类号: 

  • TP181
[1]PANG B,LEE L.Opinion mining and sentiment analysis[M].Now Publishers Inc,2008.
[2]LIU B.Sentiment analysis and opinion mining[J].SynthesisLectures on Human Language Technologies,2012,5(1):1-167.
[3]BAHDANAU D,CHO K,BENGIO Y.Neural machine translation by jointly learning to align and translate[J].arXiv:1409.0473,2014.
[4]SUN X W,WANG L,WANG X,et al.Aspect-based sentiment analysis model based on dual-attention networks[J].Journal of Computer Research and Development,2019,56(11):2384-2395.
[5]MA Y,CHENG C L.Joint left and right attention mechanismfor aspect-level text sentiment analysis[J].Application Research of Computers,2021,38(6):1753-1758.
[6]MARCHEGGIANI D,TITOV I.Encoding sentences with graph convolutional networks for semantic role labeling[C]//Procee-dings of the 2017 Conference on Empirical Methods in Natural Language Processing.2017:1506-1515.
[7]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[J].arXiv:1609.02907,2016.
[8]HU M,LIU B.Mining opinion features in customer reviews[C]//Proceedings of the 19th National Conference on Artificial intelligence.2004:755-760.
[9]DING X,LIU B,YU P S.A holistic lexicon-based approach toopinion mining[C]//Proceedings of the 2008 International Conference on Web Search and Data Mining.2008:231-240.
[10]LIU Q,LIANG B,XU J,et al.A deep hierarchical neural network model for aspect-based sentiment analysis[J].Chinese Journal of Computers,2018,41(12):3-18.
[11]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.2014:49-54.
[12]TANG D,QIN B,FENG X,et al.Effective LSTMs for target-dependent sentiment classification[C]//Proceedings of the 26th International Conference on Computational Linguistics:Technical Papers.2016:3298-3307.
[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.2016:606-615.
[14]ZHANG Z L,LI L C,ZHU X Q,et al.Aspect sentiment analysis combining on-lstm and self-attention mechanism[J].Journal of Chinese Computer Systems,2020,41(9):1839-1844.
[15]TANG D,QIN B,LIU T.Aspect level sentiment classification with deep memory network[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing.2016:214-224.
[16]MA D,LI S,ZHANG X,et al.Interactive attention networks for aspect-level sentiment classification[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence.2017:4068-4074.
[17]SONG Y,WANG J,JIANG T,et al.Attentional encoder network for targeted sentiment classification[J].arXiv:1902.09314,2019.
[18]FAN C,GAO Q,DU J,et al.Convolution-based memory net-work for aspect-based sentiment analysis[C]//Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval.2018:1161-1164.
[19]ZHANG C,LI Q,SONG D.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.
[20]SUN K,ZHANG R,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 Processing(EMNLP-IJCNLP).2019:5679-5688.
[21]ZHAO P,HOU L,WU O.Modeling sentiment dependencieswith graph convolutional networks for aspect-level sentiment classification[J].arXiv:1906.04501,2019.
[22]QI S Z,HUANG X Y,ZHU X F.Aspect-based sentiment analysis model based on weight enhancement[J/OL].Journal of Chinese Computer Systems,2021:1-8.https://kns.cnki.net/kcms/detail/21.1106.TP.20210319.1014.012.html.
[23]ZHOU J,HUANG J X,HU Q V,et al.SK-GCN:Modeling syntax and knowledge via graph convolutional network for aspect-level sentiment classification[J/OL].Knowledge-Based Systems,2020,205:106292.https://doi.org/10.1016/j.knosys.2020.106292.
[24]PENNINGTON J,SOCHER R,MANNINGG C D.Glove:Glo-bal vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing.2014:1532-1543.
[25]KENTON J D M W C,TOUTANOVA L K.BERT:Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of Annual Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2019:4171-4186.
[26]PHAN M H,OGUNBONA P O.Modelling context and syntactical features for aspect-based sentiment analysis[C]//Procee-dings of the 58th Annual Meeting of the Association for Computational Linguistics.2020:3211-3220.
[27]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.
[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.2015:486-495.
[29]PONTIKI M,GALANIS D,PAPAGEORGIOU H,et al.SemEval-2016 Task 5:Aspect based sentiment analysis[C]//Procee-dings of the 10th International Workshop on Semantic Evaluation.2016:19-30.
[30]HUANG B,OU Y,CARLEY K M.Aspect levelsentiment classification with attention-over-attention neural networks[C]//Proceedings of the International Conference on Social Computing,Behavioral-Cultural Modeling and Prediction and Behavior Representation in Modeling and Simulation.Cham:Springer,2018:197-206.
[31]HUANG B,CARLEY K M.Syntax-aware aspect level senti-ment classification with graph attention networks[C]//Procee-dings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJCNLP).2019:5469-5477.
[32]KUMAR A,NARAPAREDDY V T,SRIKANTHrikanth V A,et al.Aspect-based sentiment classification using interactive gated convolutional network[J].IEEE Access,2020,8:22445-22453.
[33]XIAO L,HU X,CHEN Y,et al.Targeted sentiment classification based on attentional encoding and graph convolutional networks[J/OL].Applied Sciences,2020,10(3):957https://doi.org/10.3390/app10030957.
[1] 雪峰豪, 蒋海波, 唐聃.
深度学习在健康医疗中的应用研究综述
Review of Deep Learning Applications in Healthcare
计算机科学, 2023, 50(4): 1-15. https://doi.org/10.11896/jsjkx.220600166
[2] 韩雪明, 贾彩燕, 李轩涯, 张鹏飞.
传播树结构结点及路径双注意力谣言检测模型
Dual-attention Network Model on Propagation Tree Structures for Rumor Detection
计算机科学, 2023, 50(4): 22-31. https://doi.org/10.11896/jsjkx.220200037
[3] 刘泽润, 郑红, 邱俊杰.
基于抽象语法树裁剪的智能合约漏洞检测研究
Smart Contract Vulnerability Detection Based on Abstract Syntax Tree Pruning
计算机科学, 2023, 50(4): 317-322. https://doi.org/10.11896/jsjkx.220300063
[4] 李帅, 徐彬, 韩祎珂, 廖同鑫.
SS-GCN:情感增强和句法增强的方面级情感分析模型
SS-GCN:Aspect-based Sentiment Analysis Model with Affective Enhancement and Syntactic Enhancement
计算机科学, 2023, 50(3): 3-11. https://doi.org/10.11896/jsjkx.220700238
[5] 邓亮, 齐攀虎, 刘振龙, 李敬鑫, 唐积强.
BGPNRE:一种基于BERT的全局指针网络实体关系联合抽取方法
BGPNRE:A BERT-based Global Pointer Network for Named Entity-Relation Joint Extraction Method
计算机科学, 2023, 50(3): 42-48. https://doi.org/10.11896/jsjkx.220600239
[6] 陈姝睿, 梁子然, 饶洋辉.
细粒度语义知识图谱增强的中文OOV词嵌入学习
Fine-grained Semantic Knowledge Graph Enhanced Chinese OOV Word Embedding Learning
计算机科学, 2023, 50(3): 72-82. https://doi.org/10.11896/jsjkx.220700249
[7] 周明强, 代开浪, 吴全旺, 朱庆生.
异构信息网络的注意力感知多通道图卷积评分预测模型
Attention-aware Multi-channel Graph Convolutional Rating Prediction Model for Heterogeneous Information Networks
计算机科学, 2023, 50(3): 129-138. https://doi.org/10.11896/jsjkx.220300004
[8] 董永峰, 黄港, 薛婉若, 李林昊.
融合IRT的图注意力深度知识追踪模型
Graph Attention Deep Knowledge Tracing Model Integrated with IRT
计算机科学, 2023, 50(3): 173-180. https://doi.org/10.11896/jsjkx.211200134
[9] 华晓凤, 冯娜, 于俊清, 何云峰.
基于规则推理的足球视频任意球射门事件检测
Shooting Event Detection of Free Kick in Soccer Video Based on Rule Reasoning
计算机科学, 2023, 50(3): 181-190. https://doi.org/10.11896/jsjkx.220300062
[10] 梅鹏程, 杨吉斌, 张强, 黄翔.
一种基于三维卷积的声学事件联合估计方法
Sound Event Joint Estimation Method Based on Three-dimension Convolution
计算机科学, 2023, 50(3): 191-198. https://doi.org/10.11896/jsjkx.220500259
[11] 白雪飞, 马亚楠, 王文剑.
基于特征融合的边缘引导乳腺超声图像分割方法
Segmentation Method of Edge-guided Breast Ultrasound Images Based on Feature Fusion
计算机科学, 2023, 50(3): 199-207. https://doi.org/10.11896/jsjkx.211200294
[12] 刘航, 普园媛, 吕大华, 赵征鹏, 徐丹, 钱文华.
极化自注意力约束颜色溢出的图像自动上色
Polarized Self-attention Constrains Color Overflow in Automatic Coloring of Image
计算机科学, 2023, 50(3): 208-215. https://doi.org/10.11896/jsjkx.220100149
[13] 陈亮, 王璐, 李生春, 刘昌宏.
基于深度学习的可视化仪表板生成技术研究
Study on Visual Dashboard Generation Technology Based on Deep Learning
计算机科学, 2023, 50(3): 238-245. https://doi.org/10.11896/jsjkx.230100064
[14] 张译, 吴秦.
特征增强损失与前景注意力人群计数网络
Crowd Counting Network Based on Feature Enhancement Loss and Foreground Attention
计算机科学, 2023, 50(3): 246-253. https://doi.org/10.11896/jsjkx.220100219
[15] 刘哲, 殷成凤, 李天瑞.
基于BERT和多特征融合嵌入的中文拼写检查
Chinese Spelling Check Based on BERT and Multi-feature Fusion Embedding
计算机科学, 2023, 50(3): 282-290. https://doi.org/10.11896/jsjkx.220100104
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!