计算机科学 ›› 2023, Vol. 50 ›› Issue (3): 3-11.doi: 10.11896/jsjkx.220700238

• 知识图谱赋能的知识工程:理论、技术与系统专题 • 上一篇    下一篇

SS-GCN:情感增强和句法增强的方面级情感分析模型

李帅, 徐彬, 韩祎珂, 廖同鑫   

  1. 东北大学计算机科学与工程学院 沈阳 110819
  • 收稿日期:2022-07-24 修回日期:2022-12-06 出版日期:2023-03-15 发布日期:2023-03-15
  • 通讯作者: 徐彬(xubin@mail.neu.edu.cn)
  • 作者简介:(lishuai@stumail.neu.edu.cn)
  • 基金资助:
    中央高校基本科研业务费专项资金(N2116019);辽宁省自然科学基金面上项目 (2022-MS-119);全国高等院校计算机基础教育研究会计算机基础教育教学研究课题(2022-AFCEC-237)

SS-GCN:Aspect-based Sentiment Analysis Model with Affective Enhancement and Syntactic Enhancement

LI Shuai, XU Bin, HAN Yike, LIAO Tongxin   

  1. School of Computer Science and Engineering,Northeastern University,Shenyang 110819,China
  • Received:2022-07-24 Revised:2022-12-06 Online:2023-03-15 Published:2023-03-15
  • About author:LI Shuai,born in 1998,postgraduate.His main research interests include affective computing and aspect-level sentiment analysis.
    XU Bin,born in 1980,Ph.D,associate professor,is a member of China Computer Federation.His main research interests include artificial intelligence and smart education.
  • Supported by:
    Fundamental Research Funds for the Central Universities(N2116019),Liaoning Natural Science Foundation(2022-MS-119) and Teaching Research Project of Computer Basic Education of AFCEC(2022-AFCEC-237).

摘要: 方面级情感分析(Aspect-Based Sentiment Analysis,ABSA)作为知识图谱下游应用,属于细粒度情感分析任务,旨在理解人们对评价目标在方面层次的情感极性。近年来,相关研究已经取得显著进步,但现有方法侧重于利用句子内的顺序性或句法依赖约束,而没有充分利用上下文词与方面词之间的依赖类型。此外,现有的基于图卷积神经网络模型对节点特征保留的能力不足。针对该问题,首先,在句法依赖树的基础上,充分挖掘上下文词与方面词之间的依赖类型,将其融入依赖图的构建;其次,定义了一个“敏感关系集合”,利用它来构建辅助句以增强特定上下文词与方面词之间的关联性,同时结合情感知识网络SenticNet以增强句子的依赖图,进而改进图神经网络的构建;最后,引入上下文保留机制,来减小节点特征在多层图卷积神经网络中的信息损失。提出的SS-GCN模型将并行学习到的句法表示和上下文表示进行融合以完成情感增强和句法增强。在3个公开数据集上进行了广泛的实验,证明了SS-GCN的有效性。

关键词: 方面级情感分析, 图卷积神经网络, SenticNet, 注意力机制, Bi-LSTM

Abstract: Aspect-based sentiment analysis(ABSA),as a downstream application of knowledge graph,belongs to the fine-grained sentiment analysis task,which aims to understand the sentiment polarity of people on the evaluation target at the aspect level.Relevant research in recent years has made significant progress,but existing methods focus on exploiting sequentiality or syntactic dependency constraints within sentences,and do not fully exploit the type of dependencies between context words and aspect words.In addition,the existing graph-based convolutional neural network models have insufficient ability to retain node features.In response to this problem,firstly,based on the syntactic dependency tree,this paper fully excavates the dependency types between context words and aspect words,and integrates them into the construction of the dependency graph.Second,we define a “sensitive relation set”,which is used to construct auxiliary sentences to enhance the correlation between specific context words and aspect words,and at the same time,combined with the sentiment knowledge network SenticNet to enhance the sentence dependency graph,and then improve the construction of the graph neural network.Finally,a context retention mechanism is introduced to reduce the information loss of node features in the multilayer graph convolution neural network.The proposed SS-GCN model fuses the syntactic and contextual representations learned in parallel to accomplish sentiment enhancement and syntactic enhancement,and extensive experiments on three public datasets demonstrate the effectiveness of SS-GCN.

Key words: Aspect-level sentiment analysis, Graph convolutional networks, SenticNet, Attention mechanism, Bi-LSTM

中图分类号: 

  • TP391
[1]ZHANG C,LI Q,SONG D.Aspect-based sentiment classification with aspect-specific graph convolutional networks[J].ar-Xiv:1909.03477,2019.
[2]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].Knowledge-Based Systems,2020(205):106292.
[3]LIANG B,SU H,GUI L,et al.Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks[J].Knowledge-Based Systems,2021,235:107643.
[4]CAMBRIA E,SPEER R,HAVASI C,et al.SenticNet:A publicly available semantic resource for opinion mining[C]//AAAI CSK.Arlington,2010:14-18.
[5]CAMBRIA E,HAVASI C,HUSSAIN A.Senticnet 2:A semantic and affective resource for opinion mining and sentiment ana-lysis[C]//Twenty-Fifth International FLAIRS Conference.2012:202-207.
[6]CAMBRIA E,OLSHER D,RAJAGOPAL D.SenticNet 3:acommon and common-sense knowledge base for cognition-driven sentiment analysis[C]//Twenty-eighth AAAI Conference on Artificial Intelligence.2014:1515-1521.
[7]CAMBRIAE,PORIA S,BAJPAI R,et al.SenticNet 4:A semantic resource for sentiment analysis based on conceptual primitives[C]//Proceedings of COLING 2016,the 26th International Conference on Computational Linguistics:Technical papers.2016:2666-2677.
[8]CAMBRIA E,PORIA S,HAZARIKA D,et al.SenticNet 5:Discovering conceptual primitives for sentiment analysis by means of context embeddings[C]//Proceedings of the AAAI Confe-rence on Artificial Intelligence.2018:1795-1802.
[9]CAMBRIA E,LI Y,XING F Z,et al.SenticNet 6:Ensemble application of symbolic and subsymbolic AI for sentiment analysis[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management.2020:105-114.
[10]QI P,ZHANG Y,ZHANG Y,et al.Stanza:A Python natural languageprocessing toolkit for many human languages[J].ar-Xiv:2003.07082,2020.
[11]TANG D,QIN B,FENG X,et al.Effective LSTMs for target-dependent sentiment classification[J].arXiv:1512.01100,2015.
[12]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.
[13]MA D,LI S,ZHANG X,et al.Interactive attention networks for aspect-level sentiment classification[J].arXiv:1709.00893,2017.
[14]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.
[15]LI C B,ZHAO L,LI X G,et al.Text Sentiment Classification Model Based on TF-IDF Weighted Convolutional Neural Network[J].Journal of Chongqing University of Technology(Natural Science),2021,35(11):109-115.
[16]XUE W,LI T.Aspect Based Sentiment Analysis with GatedConvolutional Networks[J/OL].https://arxiv.org/abs/1805.07043.
[17]LI X,BING L,LAM W,et al.Transformation networks for target-oriented sentiment classification[J].arXiv:1805.01086,2018.
[18]HOU X,QI P,WANG G,et al.Graph ensemble learning overmultiple dependency trees for aspect-level sentiment classification[J].arXiv:2103.11794,2021.
[19]WANG K,SHEN W,YANG Y,et al.Relational graph attention network for aspect-based sentiment analysis[J].arXiv:2004.12362,2020.
[20]LI R,CHEN H,FENG F,et al.Dual Graph Convolutional Networks for Aspect-based Sentiment Analysis[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing.2021.
[21]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].Knowledge-Based Systems,2020,205(3):106292.
[22]XING F Z,PALLUCCHINI F,CAMBRIA E.Cognitive-inspired domain adaptation of sentiment lexicons[J].Information Processing & Management,2019,56(3):554-564.
[23]ZHONG Q,DING L,LIU J,et al.Knowledge Graph Augmented Network Towards Multiview Representation Learning forAspect-based Sentiment Analysis[J].arXiv:2201.04831,2022.
[24]LI M,LU Q,LONG Y,et al.Inferring affective meanings of words from word embedding[J].IEEE Transactions on Affective Computing,2017,8(4):443-456.
[25]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 Proces-sing(EMNLP).2014:1532-1543.
[26]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.
[27]CHEN Y.Convolutional neural network forsentence classifica-tion[D].Waterloo:University of Waterloo,2015.
[28]MARIA P,DIMITRIS G,JOHNP,et al.SemEval-2014 Task 4:Aspect Based Sentiment Analysis[C]//Proceedings of the 8th International Workshop on Semantic Evaluation(SemEval 2014).2014:27-35.
[29]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.
[30]TANG J,LU Z,SU J,et al.Progressive self-supervised attention learning for aspect-level sentiment analysis[J].arXiv:1906.01213,2019.
[31]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.2018:3433-3442.
[32]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.
[33]ZHU X,ZHU L,GUO J,et al.GL-GCN:Global and local dependency guided graph convolutional networks for aspect-based sentiment classification[J].Expert Systems with Applications,2021,186:115712.
[34]MA Y,PENG H,KHAN T,et al.Sentic LSTM:a hybrid network for targeted aspect-based sentiment analysis[J].Cognitive Computation,2018,10(4):639-650.
[35]WU S,XU Y,WU F,et al.Aspect-based sentiment analysis via fusing multiple sources of textual knowledge[J].Knowledge-Based Systems,2019,183:104868.
[36]LAI S,XU L,LIU K,et al.Recurrent convolutional neural networks for text classification[C]//Twenty-ninth AAAI Confe-rence on Artificial Intelligence.2015:2267-2273.
[1] 陈富强, 寇嘉敏, 苏利敏, 李克.
基于图神经网络的多信息优化实体对齐模型
Multi-information Optimized Entity Alignment Model Based on Graph Neural Network
计算机科学, 2023, 50(3): 34-41. https://doi.org/10.11896/jsjkx.220700242
[2] 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
[3] 冯程程, 刘派, 姜琳颖, 梅笑寒, 郭贵冰.
文档增强型知识库问答
Document-enhanced Question Answering over Knowledge-Bases
计算机科学, 2023, 50(3): 266-275. https://doi.org/10.11896/jsjkx.220300022
[4] 邹芸竹, 杜圣东, 滕飞, 李天瑞.
一种基于多模态深度特征融合的视觉问答模型
Visual Question Answering Model Based on Multi-modal Deep Feature Fusion
计算机科学, 2023, 50(2): 123-129. https://doi.org/10.11896/jsjkx.211200303
[5] 王鹏宇, 台文鑫, 刘芳, 钟婷, 罗绪成, 周帆.
基于数据增强的自监督飞行航迹预测
Self-supervised Flight Trajectory Prediction Based on Data Augmentation
计算机科学, 2023, 50(2): 130-137. https://doi.org/10.11896/jsjkx.211200016
[6] 瞿中, 王彩云.
基于注意力机制和轻量级空洞卷积的混凝土路面裂缝检测
Crack Detection of Concrete Pavement Based on Attention Mechanism and Lightweight DilatedConvolution
计算机科学, 2023, 50(2): 231-236. https://doi.org/10.11896/jsjkx.211200290
[7] 刘露平, 周欣, 程军军, 何小海, 卿粼波, 王美玲.
基于会话式机器阅读理解模型的事件抽取方法
Event Extraction Method Based on Conversational Machine Reading Comprehension Model
计算机科学, 2023, 50(2): 275-284. https://doi.org/10.11896/jsjkx.220400271
[8] 曹金娟, 钱忠, 李培峰.
基于联合模型的端到端事件可信度识别
End-to-End Event Factuality Identification with Joint Model
计算机科学, 2023, 50(2): 292-299. https://doi.org/10.11896/jsjkx.211200108
[9] 蔡肖, 陈志华, 盛斌.
基于移位窗口金字塔Transformer的遥感图像目标检测
SPT:Swin Pyramid Transformer for Object Detection of Remote Sensing
计算机科学, 2023, 50(1): 105-113. https://doi.org/10.11896/jsjkx.211100208
[10] 张婧媛, 王宏霞, 何沛松.
基于Transformer的多任务图像拼接篡改检测算法
Multitask Transformer-based Network for Image Splicing Manipulation Detection
计算机科学, 2023, 50(1): 114-122. https://doi.org/10.11896/jsjkx.211100269
[11] 李雪辉, 张拥军, 史殿习, 徐化池, 史燕燕.
融合注意力特征的无锚框视觉目标跟踪方法
AFTM:Anchor-free Object Tracking Method with Attention Features
计算机科学, 2023, 50(1): 138-146. https://doi.org/10.11896/jsjkx.211000083
[12] 赵倩, 周冬明, 杨浩, 王长城.
残差注意力与多特征融合的图像去模糊
Image Deblurring Based on Residual Attention and Multi-feature Fusion
计算机科学, 2023, 50(1): 147-155. https://doi.org/10.11896/jsjkx.211100161
[13] 郑诚, 梅亮, 赵伊研, 张苏航.
基于双向注意力机制和门控图卷积网络的文本分类方法
Text Classification Method Based on Bidirectional Attention and Gated Graph Convolutional Networks
计算机科学, 2023, 50(1): 221-228. https://doi.org/10.11896/jsjkx.211100095
[14] 周芳泉, 成卫青.
基于全局增强图神经网络的序列推荐
Sequence Recommendation Based on Global Enhanced Graph Neural Network
计算机科学, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085
[15] 戴禹, 许林峰.
基于文本行匹配的跨图文本阅读方法
Cross-image Text Reading Method Based on Text Line Matching
计算机科学, 2022, 49(9): 139-145. https://doi.org/10.11896/jsjkx.220600032
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!