计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (10): 193-202.doi: 10.11896/jsjkx.220900192

• 人工智能 • 上一篇    下一篇

基于方面语义和门控过滤网络的方面级情感分析

何智豪1, 陈红梅2, 罗川3   

  1. 1 西南交通大学唐山研究院 河北 唐山063000
    2 西南交通大学计算机与人工智能学院 成都611756
    3 四川大学计算机学院 成都610065
  • 收稿日期:2022-09-20 修回日期:2022-12-07 出版日期:2023-10-10 发布日期:2023-10-10
  • 通讯作者: 陈红梅(hmchen@swjtu.edu.cn)
  • 作者简介:(zhhe@my.swjtu.edu.cn)
  • 基金资助:
    国家自然科学基金(61976182,62076171);四川省自然科学基金(2022NSFSC0898)

Aspect-based Sentiment Analysis Based on Aspect Semantic and Gated Filtering Network

HE Zhihao1, CHEN Hongmei2, LUO Chuan3   

  1. 1 Tangshan Research Institute,Southwest Jiaotong University,Tangshan,Hebei 063000,China
    2 School of Computing and Artificial Intelligence,Southwest Jiaotong University,Chengdu 611756,China
    3 College of Computer Science,Sichuan University,Chengdu 610065,China
  • Received:2022-09-20 Revised:2022-12-07 Online:2023-10-10 Published:2023-10-10
  • About author:HE Zhihao,born in 1998,postgraduate.His main research interests include intelligent information processing and sentiment analysis.CHEN Hongmei,born in 1971,Ph.D,professor,Ph.D.supervisor,is a member of China Computer Federation.Her main research interests include intelligent information processing,pattern recognition,etc.
  • Supported by:
    National Natural Science Foundation of China(61976182,62076171) and Natural Science Foundation of Sichuan Province,China(2022NSFSC0898).

PDF (PC)

1910

摘要： 方面级情感分析(Aspect-based Sentiment Analysis,ABSA)是一项细粒度的情感分析任务,旨在预测文本中特定方面的情感极性。目前,鉴于循环神经网络在序列建模方面的卓越性能以及卷积神经网络学习局部模式的出色表现,部分工作将两者相结合来挖掘情感信息,并且取得了不错的效果。但是,少有工作在将两者结合后应用到方面级情感分析任务中的同时考虑方面信息。在方面级情感分析任务中,大部分工作将方面视作一个独立整体与上下文进行交互,但是对于方面的表示过于简单,缺乏真实语义。针对上述问题,文中提出了一种基于方面语义和门控过滤网络(Aspect Semantic and Gated Filtering Network,ASGFN)的神经网络模型,用于挖掘方面级情感信息。首先,设计了方面编码模块,用于捕捉特定语境下的方面语义信息,该模块基于全局上下文融合多头注意机制与图卷积神经网络构建包含特定语义的方面表示。其次,设计门控过滤网络连接循环神经网络和卷积神经网络,以此增强方面与上下文的交互,同时结合循环神经网络与卷积神经网络的优势,进而提取情感特征。最后,将情感特征与方面表示相结合,生成预测情感极性的语义表征。在restaurant,laptop和twitter这3个公用数据集上分别取得了84.72%,78.64%,76.22%的情感分类准确率。实验结果表明了所提模型的有效性,它能提高方面级情感分类任务的性能。

关键词: 方面级情感分析, 方面语义, 门控过滤, 循环神经网络, 卷积神经网络

Abstract: Aspect-based sentiment analysis(ABSA)is a fine-grained sentiment analysis,which aims to predict sentiment polarity of text toward a specific aspect.Currently,given the excellent capabiities of recurrent neural networks(RNN) in sequence mode-ling and the outstanding performance of convolutional neural networks(CNN) in learning local patterns,some works have combined the two to mine sentiment information and achieved good results.However,few works consider aspect information while applying the combination of the two to ABSA.In aspect-based sentiment analysis tasks,most of the work treat aspect as an independent whole interacting with the contexts,but the representation of aspect is too simple and lacks real semantic.To address the above issues,this paper proposes a neural network model based on aspect semantic and gated filtering network(ASGFN) to better mine aspect-based sentiment information.First,an aspect encoding module is designed to capture context-specific aspect semantic information,which is based on a global context fusion multi-head attention mechanism with a graph convolutional neural network to construct aspect representation containing specific semantic.Second,a gated filtering network is designed to connect RNN and CNN as a way to enhance the interaction of aspect with the contexts,while combining the advantages of the RNN and the CNN,and then extracting the sentiment feature.Eventually,the sentiment feature is combined with aspect representation to generate semantic representation that predicts sentiment polarity.Sentiment classification accuracies of 84.72%,78.64%,and 76.22% are achieved in three communal datasets,restaurant,laptop,and twitter,respectively.Experimental results demonstrate the effectiveness of the proposed model,which can improve the performance of ABSA.

Key words: Aspect-based sentiment analysis, Aspect semantic, Gated filtering, RNN, CNN

中图分类号: 

  • TP391
[1]SCHOUTEN K,FRASINCAR F.Survey on aspect-level sentiment analysis [J].IEEE Transactions on Knowledge and Data Engineering,2015,28(3):813-830.
[2]MA D,LI S,WU F,et al.Exploring sequence-to-sequencelearning in aspect term extraction[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.2019:3538-3547.
[3]HU M,ZHAO S,GUO H,et al.Multi-Label Few-Shot Learning for Aspect Category Detection[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing(Volume 1:Long Papers).2021:6330-6340.
[4]WU M,WANG W,PAN S J.Deep weighted MaxSAT for aspect-based opinion extraction[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural LanguageProces-sing(EMNLP).2020:5618-5628.
[5]TANG D,QIN B,FENG X,et al.Effective lstms for target-dependent sentiment classification[C]//Proceedings of COLING 2016,the 26th International Conference on Computational Linguistics:Technical Papers.2016:3298-3307.
[6]ZHANG W,DENG Y,LI X,et al.Aspect Sentiment Quad Prediction as Paraphrase Generation[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Proces-sing.2021:9209-9219.
[7]CAI H,XIA R,YU J.Aspect-category-opinion-sentiment quadruple extraction with implicit aspects and opinions[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing(Volume 1:Long Papers).2021:340-350.
[8]DENG S,SINHA A P,ZHAO H.Adapting sentiment lexicons to domain-specific social media texts [J].Decision Support Systems,2017,94:65-76.
[9]PORIA S,CAMBRIA E,WINTERSTEIN G,et al.Sentic pat-terns:dependency-based rules for concept-level sentiment analysis [J].Knowledge-Based Systems,2014,69:45-63.
[10]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(SemEval 2014).2014:437-442.
[11]JIANG L,YU M,ZHOU M,et al.Target-Dependent twittersentiment classification[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics:Human Language Technologies.2011:151-160.
[12]ELMAN J L.FINDING structure in time [J].CognitiveScience,1990,14(2):179-211.
[13]KALCHBRENNER N,GREFENSTETTE E,BLUNSOM P.A convolutional neural network for modelling sentences[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics(Volume 1:Long Papers).2014:655-665.
[14]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(Volume 2:Short papers).2014:49-54.
[15]NGUYEN T H,SHIRAI K.Phrasernn:phrase recursive neural network for aspect-based sentiment analysis[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.2015:2509-2514.
[16]HOCHREITER S,SCHMIDHUBER J.Long short-term memo-ry [J].Neural Computation,1997,9(8):1735-1780.
[17]BASIRI M E,NEMATI S,ABDAR M,et al.ABCDM:An attention-based bidirectional CNN-RNN deep model for sentiment analysis [J].Future Generation Computer Systems,2021,115:279-294.
[18]LI W,ZHU L,SHI Y,et al.User reviews:Sentiment analysisusing lexicon integrated two-channel CNN-LSTM family models [J].Applied Soft Computing,2020,94:106435.
[19]HU Y L,TONG T Q,ZHANG X Y,et al.Self-attention-based BGRU and CNN for sentiment analysis [J].Computer Science,2022,49(1):252-258.
[20]WANG Y,HUAN G M,ZHAO L,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.
[21]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.
[22]LIANG B,LUO W,LI X,et al.Enhancing aspect-based sentiment analysis with supervised contrastive learning[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management.2021:3242-3247.
[23]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[C]//5th International Confe-rence on Learning Representations.2016.
[24]BAHDANAU D,CHO K H,BENGIO Y.Neuralmachine translation by Jointly learning to align and translate[C]//3rd International Conference on Learning Representations.2015.
[25]KUMAR A,IRSOY O,ONDRUSKA P,et al.Ask me anything:Dynamic memory networks for natural language processing[C]//International Conference on Machine Learning.PMLR,2016:1378-1387.
[26]MA D,LI S,ZHANG X,et al.Interactive attention networks foraspect-level sentiment classification[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence.2017:4068-4074.
[27]YANG C,ZHANG H,JIANG B,et al.Aspect- based sentiment analysis with alternating coattention networks [J].Information Processing & Management,2019,56(3):463-478.
[28]JIANG N,TIAN F,LI J,et al.MAN:mutual attention neural networks model for aspect-level sentiment classification in SIoT [J].IEEE Internet of Things Journal,2020,7(4):2901-2913.
[29]TANG D,QIN B,LIU T.Aspect level sentiment classificationwith deep memory Network[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing.2016:214-224.
[30]LV Y,WEI F,CAO L,et al.Aspect-level sentiment analysisusing context and aspect memory network [J].Neurocompu-ting,2021,428:195-205.
[31]WU C,XIONG Q,YANG Z,et al.Residual attention and other aspects module for aspect-based sentiment analysis[J].Neurocomputing,2021,435:42-52.
[32]XU Q,ZHU L,DAI T,et al.Aspect-based sentiment classification with multi-attention network [J].Neurocomputing,2020,388:135-143.
[33]XUE W,LI T.Aspect based sentiment analysis with gated con-volutional networks [C]//Proceedings of the 56th Annual Mee-ting of the Association for Computational Linguistics(Volume 1:Long Papers).2018:2514-2523.
[34]PIAO G,BRESLIN J G.FINANCIAL aspect and sentiment pre-dictions with deep neural networks:an ensemble approach[C]//Companion Proceedings of the The Web Conference 2018.2018:1973-1977.
[35]SUN Z F,WANG J.RCNN-BGRU-HN networkmodel for aspect-based sentiment analysis [J].Computer Science,2019,46(9):223-228.
[36]TAO Y C,WU W L,WU L,et al.Aspect-based SentimentAnalysis of Multi-channel Based on Attention Mechanism and Sentiment Information [J].Journal of Chinese Computer Systems,2022,43(7):1406-1412.
[37]LI R,CHEN H,FENG F,et al.Dual graph convolutional net-works 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 Na-tural Language Processing(Volume1:Long Papers).2021:6319-6329.
[38]DEVLIN J,CHANG M W,LEE K,et al.Bert:Pretraining ofdeep bidirectional transformers for language understanding [J].arXiv:1810.04805,2018.
[39]LI X,BING L,LAM W,et al.Transformation networks for target-oriented sentiment classification[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics(Volume 1:Long Papers).2018:946-956.
[40]SONG W,WEN Z,XIAO Z,et al.Semantics perception and refinement network for aspect-based sentiment analysis [J].Knowledge-Based Systems,2021,214:106755.
[41]ZHANG C,LI Q,SONG D.Aspect-based sentiment classifica-tion 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.
[42]WANG K,SHEN W,YANG Y,et al.Relational graph attention network for aspect-based sentiment analysis[C]//Proceedings of the 58th Annual Meeting of the Association for Computa-tional Linguistics.2020:3229-3238.
[43]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.
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