文本细粒度情绪识别方法与应用综述

doi:10.11896/jsjkx.220900137

摘要/Abstract

摘要： 互联网中海量文本包含的情绪信息,表达着公众观点与态度,如何识别与利用情绪资源已成为各领域的研究焦点。通过梳理细粒度情绪识别相关理论与文献,从分类方法与应用场景两方面进行总结归纳,讨论情绪识别技术面临的挑战及实践缺口。通过分析发现,细粒度情绪识别主要有基于情绪词典、统计机器学习与神经网络学习的方法,且多应用于商务分析与舆情管理中。针对未来研究趋势,首先可对网络情绪词实时更新、领域词典构建及语义分析等技术展开研究;其次,如何提升训练数据分类自动化、打造半监督学习模型亟待深入探讨;此外,商务分析与舆情管理的研究,可开展对方面提取与情绪识别融合的探索。文中对情绪识别技术与应用的总结评述,有望为后续研究提供参考。

关键词: 细粒度情绪识别, 情绪分类, 情绪词典, 机器学习, 神经网络学习

Abstract: Emotional information contained in massive texts on the Internet expresses public views and attitudes.How to identify and utilize emotional resources has become the focus of research in various fields.By combing the relevant theories and literature on fine-grained emotion recognition,this paper summarizes the classification methods and application scenarios,and discusses the technical challenges and practical gaps.Through analysis,it is found that fine-grained emotion recognition methods mainly include emotion lexicon,traditional machine learning and neural network learning,which are mostly used in business analysis and public opinion management.In view of the future research trend,firstly,the real-time updating of online emotion words,domain lexicon construction and semantic analysis technology can be studied.Secondly,how to improve the automatic classification of training data and build a semi-supervised learning model need to be further discussed.In addition,the research of business analysis and public opinion management can explore the integration of aspect extraction and emotion recognition.This paper summarizes and comments on emotion recognition technology and its application,which can provide a reference for the subsequent research.

Key words: Fine-grained emotion recognition, Emotion classification, Emotion lexicon, Machine learning, Neural network learning

中图分类号:

TP391

王希雅, 张宁, 程馨. 文本细粒度情绪识别方法与应用综述[J]. 计算机科学, 2023, 50(6A): 220900137-7. https://doi.org/10.11896/jsjkx.220900137

WANG Xiya, ZHANG Ning, CHENG Xin. Review on Methods and Applications of Text Fine-grained Emotion Recognition[J]. Computer Science, 2023, 50(6A): 220900137-7. https://doi.org/10.11896/jsjkx.220900137

参考文献

[1]CARDONE B,MARTINO F D,SENATORE S.Improving theemotion-based classification by exploiting the fuzzy entropy in FCM clustering[J].International Journal of Intelligent Systems,2021,36(11):6944-6967.
[2]LI L,WANG Z,ZHANG Q,et al.Effect of anger,anxiety,and sadness on the propagation scale of social media posts after na-tural disasters[J].Information Processing & Management,2020,57(6):102313.
[3]WANG Z,HO S B,CAMBRIA E.A review of emotion sensing:categorization models and algorithms[J].Multimedia Tools and Applications,2020,79(47):35553-35582.
[4]LI W,XU H.Text-based emotion classification using emotion cause extraction[J].Expert Systems with Applications,2014,41(4):1742-1749.
[5]NANDWANI P,VERMA R.A review on sentiment analysis and emotion detection from text[J].Social Network Analysis and Mining,2021,11(1):1-19.
[6]ZHANG W,WANG M,ZHU Y.Does government information release really matter in regulating contagion-evolution of negative emotion during public emergencies? From the perspective of cognitive big data analytics[J].International Journal of Information Management,2020,50:498-514.
[7]WU P,LI X,SHEN S,et al.Social media opinion summarization using emotion cognition and convolutional neural networks[J].International Journal of Information Management,2020,51:101978.
[8]BI W,XIE Y,DONG Z,et al.Enterprise strategic management from the perspective of business ecosystem construction based on multimodal emotion recognition[J].Frontiers in Psychology,2022,13:857-891.
[9]CHAN S W K.Multilabel emotion tagging for domain-specific Texts[J].IEEE Transactions on Computational Social Systems,2021,9(4):1197-1210.
[10]EKMAN P M,FRIESEN W V,ELLSWORTH P C.Emotion in the human face:Guidelines for research and an integration of findings[M].New York:Acadmic Press,1972.
[11]PLUTCHIK R,KELLERMAN H.Emotion:Theory,research,and experience[M].New York:Acadmic Press,1986.
[12]XU L,LIN H,PAN Y,et al.Constructing the affective lexicon ontology[J].Journal of the China Society for Scientific and Technical Information,2008,27(2):6.
[13]ZHANG H,WANG D,XU H,et al.Sentiment classification of micro-blog public opinion based on convolution neural network[J].Journal of the China Society for Scientific and Technical Information,2018,37(7):695-702.
[14]DUN X,ZHANG Y,YANG K.Fine-grained sentiment analysis based on Weibo[J].Data Analysis and Knowledge Discovery,2017,1(7):61-72.
[15]YADOLLAHI A,SHAHRAKI A G,ZAIANE O R.Currentstate of text sentiment analysis from opinion to emotion mining[J].ACM Computing Surveys,2017,50(2):1-33.
[16]KUSEN E,CASCAVILLA G,FIGL K,et al.Identifying emotions in social media:comparison of word-emotion lexicons[C]//2017 5th International Conference on Future Internet of Things and Cloud Workshops.IEEE,2017:132-137.
[17]STRAPPARAVA C,VALITUTTI A.Wordnet affect:An affective extension of wordnet[J].Language Resources Evaluation,2004,4:1083-1086.
[18]MOHAMMAD S M,TURNEY P D.Emotions evoked by common words and phrases:Using mechanical turk to create an emotion lexicon[C]//Proceedings of the NAACL HLT 2010 Workshop on Computational Approaches to Analysis and Ge-neration of Emotion in Text.2010:26-34.
[19]PENNEBAKERJ W,FRANCIS M E,BOOTH R J.Linguisticinquiry and word count:LIWC 2001[R].Mahway:Lawrence Erlbaum Associates,2001.
[20]GAO R,HAO B,LI H,et al.Developing simplified Chinese psychological linguistic analysis dictionary for microblog[C]//International Conference on Brain and Health Informatics.Cham:Springer,2013:359-368.
[21]WANG Y,HUANG G,LI M,et al.Automatically constructing a fine-Grained sentiment lexicon for sentiment analysis[J].Cognitive Computation,2022,15:254-271.
[22]MOHAMMAD S M,KIRITCHENKO S.Using hashtags to capture fine emotion categories from Tweets[J].Computational Intelligence,2015,31(2):301-326.
[23]GODARD R,HOLTZMAN S.The multidimensional lexicon of emojis:A new tool to assess the emotional content of emojis[J/OL].Frontiers in Psychology,2022,13.http://doi.org/10.3389/fpsyg.2002.921388.
[24]XU L,LI L,JIANG Z,et al.A novel emotion lexicon for Chinese emotional expression analysis on Weibo:Using grounded theory and semi-automatic methods[J].IEEE Access,2020,9:92757-92768.
[25]BRUYNE L D,ATANASOVA P,AUGENSTEIN I.Joint emotion label space modeling for affect lexica[J].Computer Speech &Language,2022,71:101257.
[26]SAIF H,HE Y,FERMANDEZ M,et al.Contextual semantics for sentiment analysis of Twitter[J].Information Processing & Management,2016,52(1):5-19.
[27]ZHONG J W,LIU W,et al.Methods and applications of text sentiment analysis:A review[J].Data Analysis and Knowledge Discovery,2021,5(6):13.
[28]ASGHAR M Z,SUBHAN F,IMRAN M,et al.Performanceevaluation of supervised machine learning techniques for efficient detection of emotions from online content[J].arXiv:1908.01587,2019.
[29]PLAZA-DEL-ARCO F M,MARTIN-VALDIVIA M T,URE-NA-LOPEZ L A,et al.Improved emotion recognition in Spanish social media through incorporation of lexical knowledge[J].Future Generation Computer Systems,2020,110:1000-1008.
[30]JENA R K.Sentiment mining in a collaborative learning environment:capitalizing on big data[J].Behavior & Information Technology,2019,38(9):986-1001.
[31]CHATZAKOU D,VAKALI A,KAFETSIOS K.Detecting varia-tion of emotions in online activities[J].Expert Systems with Applications,2017,89:318-332.
[32]KOLOG E A,DEVINE S N O,ANSONG-GYIMAH K,et al.Fine-grained affect detection in learners’ generated content using machine learning[J].Education and Information Techno-logies,2019,24(6):3767-3783.
[33]LI H,CHEN Q,ZHONG Z,et al.E-word of mouth sentimentanalysis for user behavior studies[J].Information Processing & Management,2022,59(1):102784.
[34]AMEER I,SIDOROV G,GOMEZ-ADORNO H,et al.Multi-label emotion classification on code-mixed text:Data and methods[J].IEEE Access,2022,10:8779-8789.
[35]XU H,YANG W,WANG J.Hierarchical emotion classification and emotion component analysis on Chinese micro-blog posts[J].Expert Systems with Applications,2015,42(22):8745-8752.
[36]YADAV A,VISHWAKARMA D K.Sentiment analysis usingdeep learning architectures:A review[J].Artificial Intelligence Review,2020,53(6):4335-4385.
[37]KIM Y.Convolutional neural networks for sentence classifica-tion[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing.Stroudsburg:Association for Computational Linguistics,2014:1746-1751.
[38]XU D,TIAN Z,LAI R,et al.Deep learning-based emotion ana-lysis of microblog texts[J].Information Fusion,2020,64:1-11.
[39]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.Maryland,2014:49-54.
[40]HU Y.Stock forecast based on optimized LSTM model[J].Computer Science,2021,48(6A):151-157.
[41]LAI Y,ZHANG L,HAN D,et al.Fine-grained emotion classification of Chinese microblogs based on graph convolution networks[J].World Wide Web,2020,23(5):2771-2787.
[42]WANG Q,SUN L,CHEN Z.Sentiment analysis of reviewsbased on deep learning model[C]//2019 IEEE/ACIS 18th International Conference on Computer and Information Science.IEEE,2019:258-261.
[43]LEI Z,YANG Y,YANG M,et al.A multi-sentiment-resource enhanced attention network for sentiment classification[J].ar-Xiv:1807.04990,2018.
[44]SHRIVASTAVA K,KUMAR S,JAIN D K.An effective ap-proach for emotion detection in multimedia text data using sequence based convolutional neural network[J].Multimedia Tools and Applications,2019,78(20):29607-29639.
[45]LIU C,LIU T,YANG S,et al.Individual emotion recognition approach combined gated recurrent unit with emoticon distribution model[J].IEEE Access,2021,9:163542-163553.
[46]WANG J,YU L C,LAI K R,et al.Dimensional sentiment ana-lysis using a regional CNN-LSTM model[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics.2016:225-230.
[47]ZHAO R,CAI Y.Research on online marketing effects based on multi-model fusion and artificial intelligence algorithms[J].Journal of Ambient Intelligence and Humanized Computing,2021,15:1-17.
[48]AKHTAR S,GHOSAL D,EKBAL A,et al.All-in-One:Emotion,sentiment and intensity prediction using a multi-task ensemble framework[J].IEEE Transactions on Affective Computing,2019,13(1):285-299.
[49]WANG Y,FENG S,WANG D,et al.Multi-label Chinese microblog emotion classification via convolutional neural network[C]//Asia-Pacific Web Conference.Cham:Springer,2016:567-580.
[50]HE H,XIA R.Joint binary neural network for multi-label lear-ning with applications to emotion classification[C]//CCF International Conference on Natural Language Processing and Chinese Computing.Cham:Springer,2018:250-259.
[51]MORSHED S A,KHAN S S,TANVIR R B,et al.Impact ofCOVID-19 pandemic on ride-hailing services based on large-scale Twitter data analysis[J].Journal of Urban Management,2021,10(2):155-165.
[52]FELBERMAYR A,NANOPOULOS A.The role of emotionsfor the perceived usefulness in online customer reviews[J].Journal of Interactive Marketing,2016,36:60-76.
[53]SHI X,JIA M,LI J,et al.Users’ feedback on COVID-19 lock-down documentary:An emotion analysis and topic modeling analysis[J].Frontiers in Psychology,2022,13:1944049.
[54]FILIERI R,LIN Z,LI Y,et al.Customer emotions in service robot encounters:A hybrid machine-human intelligence approach[J].Journal of Service Research,2022,25(4):614-629.
[55]ZHANG W,FESENMAIERE D R.Assessing emotions in online stories:comparing self-report and text-based approaches[J].Information Technology & Tourism,2018,20(1):83-95.
[56]LUO B,ZENG J,DUAN J.Emotion space model for classifying opinions in stock message board[J].Expert Systems with Applications,2016,44:138-146.
[57]ZHANG W,WANG M,ZHU Y,et al.A hybrid neural network approach for fine-grained emotion classification and computing[J].Journal of Intelligent & Fuzzy Systems,2019,37(3):3081-3091.
[58]DHAR S,BOSE I.Emotions in Twitter communication andstock prices of firms:the impact of COVID-19 pandemic[J].Decision,2020,47(4):385-399.
[59]COOMBS W T.Protecting organization reputations during a crisis:The development and application of situational crisis communication theory[J].Corporate Reputation Review,2007,10(3):163-176.
[60]LI Q,WEI C,DANG J,et al.Tracking and analyzing publicemotion evolutions during COVID-19:A case study from the event-driven perspective on microblogs[J].International Journal of Environmental Research and Public Health,2020,17(18):6888.
[61]YANG T,XIE J,LI G,et al.Social media big data mining and spatio-temporal analysis on public emotions for disaster mitigation[J].International Journal of Geo-Information,2019,8(1):29.
[62]BHATIA S,WALASEK L,SLOVIC P,et al.The more whodie,the less we care:evidence from natural language analysis of online news articles and social media posts[J].Risk Analysis,2021,41(1):179-203.
[63]GHANBARI A F,MOSLEH M.Text emotion detection in social networks using a novel ensemble classifier based on Parzen Tree Estimator(TPE)[J].Neural Computing and Applications,2019,31(12):8971-8983.
[64]MA N,ZHANG Z,WU P.Automatic identification of term citation object with feature fusion[J].Data Analysis and Knowledge Discovery,2020,4(1):89-98.
[65]SYED A Z.Applying sentiment and emotion analysis on brand tweets for digital marketing[C]//2015 IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies.IEEE,2015:1-6.
[66]TANG X,LIU G.Research review on fine-grained sentimentanalysis[J].Library and Information Service,2017,61(5):132-140.
[67]ZHU X,SONG J,ZHANG X.Review of text emotion analysis based on topic mining technology[J].Intelligence Theory and Practice,2019,42(11):156-163.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed