计算机科学 ›› 2018, Vol. 45 ›› Issue (8): 191-197.doi: 10.11896/j.issn.1002-137X.2018.08.034

• 人工智能 • 上一篇    下一篇

基于多视角多标签学习的读者情绪分类

温雯1, 陈颖1, 蔡瑞初1, 郝志峰1,2, 王丽娟1   

  1. 广东工业大学计算机学院 广州5100001
    佛山科学技术学院数学与大数据学院 广东 佛山5280002
  • 收稿日期:2017-07-26 出版日期:2018-08-29 发布日期:2018-08-29
  • 作者简介:温 雯(1981-),女,博士,副教授,CCF会员,主要研究方向为机器学习、模式识别、信息检索,E-mail:wwen_gdut@qq.com(通信作者); 陈 颖(1993-),女,硕士生,主要研究方向为数据挖掘、模式识别,E-mail:511093965@qq.com; 蔡瑞初(1983-),男,博士,教授,CCF高级会员,主要研究方向为数据挖掘、机器学习、信息检索; 郝志峰(1968-),男,博士,教授,CCF会员,主要研究方向为机器学习、人工智能; 王丽娟(1978-),女,博士,副教授,主要研究方向为机器学习、高维数据聚类分析。
  • 基金资助:
    本文受国家自然科学基金(61202269,61472089)资助。

Emotion Classification for Readers Based on Multi-view Multi-label Learning

WEN Wen1, CHEN Ying1, CAI Rui-chu1, HAO Zhi-feng1,2, WANG Li-juan1   

  1. Department of Computers,Guangdong University of Technology,Guangzhou 510000,China1
    Department of Mathematics and Big Data,Foshan University,Foshan,Guangdong 528000,China2
  • Received:2017-07-26 Online:2018-08-29 Published:2018-08-29

摘要: 传统的读者情绪分类主要从情感分析的角度出发,着重考量读者评论中体现出来的情感极性。然而现实中,读者评论的缺失有可能影响情绪分类的有效性和及时性。如何融合包括新闻文本和评论在内的多视角信息,对读者情绪进行更加准确的研判,成为了一个具有挑战性的问题。针对这一问题,构建了一种融合多视角信息的多标签隐语义映射模型(Multi-view Multi-label Latent Indexing,MV-MLSI),将不同视角下的文本特征映射到低维语义空间,同时建立特征和标签之间的映射函数,通过最小化重构误差对模型进行求解,并设计了相关算法,从而实现对读者情绪的有效预测。相比于传统模型,该模型不仅可以充分利用多视角的信息,而且考虑了标签之间的相关性。在新闻文本数据集上的实验表明,该方法可以获得更高的准确率和稳定性。

关键词: LSI, 多标签学习, 多视角学习, 情感分析, 情绪分类

Abstract: The traditional emotion classification for readers mainly focuses on the emotional polarity embodied in the reader’s comments,which is from the perspective of sentiment analysis.However,the readers’ comments are occasio-nally not collected due to some reasons,which tends to reduce the effectiveness and timeliness of emotional classification.How to integrate the multi-perspective information,including news texts and readers’ comments,and to make a more accurate judgment of reader’s emotions has become a challenging problem.In this paper,a multi-view multi-label latent indexing (MV-MLSI) model was proposed,which maps the multi-view text features from different perspectives to the low-dimensional semantic space.Meanwhile,the mapping function among the features and labels was established,and the model could be solved by minimizing the reconstruction error.The optimization algorithm was also presented in this paper so as to make the effective prediction of reader’s emotion.Compared with the traditional model,the proposed model can not only take full advantage of multi-view information,but also take into account the correlation among labels.Experiments on the multi-view news text dataset demonstrate that the method can achieve higher accuracy and stability.

Key words: Emotion classification, Latent semantic indexing, Multi-label learning, Multi-view learning, Sentiment analysis

中图分类号: 

  • TP391
[1]TANG D,QIN B,LIU T.Document Modeling with GatedRecurrent Neural Network for Sentiment Classification[C]∥Conference on Empirical Methods in Natural Language Proces-sing.2015:1422-1432.
[2]LIU H,LI S,ZHOU G,et al.Joint Modeling of News Reader's and Comment Writer’s Emotions∥Meeting of the Association for Computational Linguistics.2013:511-515.
[3]CHEN J,LIU H H,LI S S,et al,Active Learning on NewsReader EmotionClassification[J].Journal of Shanxi University(Natural Science Edition),2017,40(1):21-26.(in Chinese)陈敬,刘欢欢,李寿山,等.基于主动学习的新闻读者情绪分类方法[J].山西大学学报(自然科学版),2017,40(1):21-26.
[4]EKMAN P.Facial expression and emotion[J].American psychologist,1993,48(4):384-392.
[5]BHOWMICK P K.Reader perspective emotion analysis in text through ensemble based multi-label classification framework[J].Computer and Information Science,2009,2(4):64.
[6]YU H,HATZIVASSILOGLOU V.Towards answering opinion questions:Separating facts from opinions and identifying the polarity of opinion sentences[C]∥Proceedings of the 2003 Confe-rence on Empirical Methods in Natural Language Processing.Association for Computational Linguistics,2003:129-136.
[7]KIM S M,HOVY E.Automatic detection of opinion bearingwords and sentences[C]∥Companion Volume to the Procee-dings of the International Joint Conference on Natural Language Processing (IJCNLP).2005:8.
[8]HU M,LIU B.Mining and summarizing customer reviews[C]∥Proceedings of the Tenth ACM SIGKDD International Confe-rence on Knowledge Discovery and Data Mining.ACM,2004:168-177.
[9]TURNEY P D.Thumbs up or thumbs down?:semantic orientation applied to unsupervised classification of reviews[C]∥Proceedings of the 40th Annual Meeting on Association for Computational Linguistics.Association for Computational Linguistics,2002:417-424.
[10]NIU Y,PAN M H,WEI O,et al.Emotion Analysis of Chinese Microblogs Using Lexicon-based Approach[J].Computer Scien-ce,2014,41(9):253-258.(in Chinese)牛耘,潘明慧,魏欧,等.基于词典的中文微博情绪识别[J].计算机科学,2014,41(9):253-258.
[11]WANG M,LIU M,FENG S,et al.A novel calibrated label ran-king based method for multiple emotions detection in Chinese microblogs[M]∥Natural Language Processing and Chinese Computing.Springer Berlin Heidelberg,2014:238-250.
[12]PANG B,LEE L,VAITHYANATHAN S.Thumbs up?:sentiment classification using machine learning techniques[C]∥Proceedings of the ACL-02 Conference on Empirical Methodsin Natural Language Processing-Volume 10.Association for Computational Linguistics,2002:79-86.
[13]YE L.Research on emotion prediction of news article from rea-der’s perspective[D].Harbin:Harbin Institute of Technology,2013.(in Chinese)叶璐.新闻文本的读者情绪自动预测方法研究[D].哈尔滨:哈尔滨工业大学,2013.
[14]WEN W,WU B,CAI R C,et al.Emotion classification for news readersbased on multi-category semantic word clusters[J].Journal of Computer Applications,2016,36(8):2076-2081.(in Chinese)温雯,吴彪,蔡瑞初,等.基于多类别语义词簇的新闻读者情绪分类[J].计算机应用,2016,36(8):2076-2081.
[15]XU R,ZOU C,XU J,et al.Reader’s Emotion Prediction Based on Partitioned Latent Dirichlet Allocation Model[C]∥Procee-dings of of International Conference on Internet Computing and Big Data.2013.
[16]LUYCKX K,VAASSEN F,PEERSMAN C,et al.Fine-grained emotion detection in suicide notes:A thresholding approach to multi-label classification[J].Biomedical Informatics Insights,2012,5(Suppl 1):61-69.
[17]LIU H H.Automatic Classification on Reader’s Emotiontowards News[D].Suzhou:Soochow University,2015.(in Chinese)刘欢欢.面向新闻的读者情绪自动分析方法研究[D].苏州:苏州大学,2015.
[18]YIN H,XU J H,XU H.A Multi-Label Classification Algorithm Bases on LS-SVM[J].Journal of Nanjing Normal University(Engineering and Technology),2010,10(2):68-73.(in Chinese)殷会,许建华,许花.基于 LS-SVM 的多标签分类算法[J].南京师范大学学报(工程技术版),2010,10(2):68-73.
[19]SHEN C B,WANG Z H,SUN Y G.A Multi-Lable Classification Algorithm Based on Label Clustering[J].SoftWare,2014,35(8):16-21.(in Chinese)申超波,王志海,孙艳歌.基于标签聚类的多标签分类算法[J].软件,2014,35(8):16-21.
[20]ZHANG M L,ZHOU Z H.ML-KNN:A lazy learning approach to multi-label learning[J].Pattern Recognition,2007,40(7):2038-2048.
[21]CABRAL R S,TORRE F,COSTEIRA J P,et al.Matrix completion for multi-label image classification[C]∥Advances in Neural Information Processing Systems.2011:190-198.
[22]WANG H,DING C,HUANG H.Multi-label linear discriminant analysis[C]∥European Conference on Computer Vision-ECCV 2010.2010:126-139.
[23]YU K,YU S,TRESP V.Multi-label informed latent semanticindexing[C]∥Proceedings of the 28th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval.ACM,2005:258-265.
[24]ZHANG M L,WU L.LIFT:Multi-label learning with label-specific features[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,37(1):107-120.
[25]GOLDBERG A,RECHT B,XU J,et al.Transduction with matrix completion:Three birds with one stone[C]∥Advances in Neural Information Processing Systems.2010:757-765.
[26]LIU M,LUO Y,TAO D,et al.Low-Rank Multi-View Learning in Matrix Completion for Multi-Label Image Classification[C]∥29th AAAI Conference on Artificial Intelligence.2015:2778-2784.
[27]XIA R,PAN Y,DU L,et al.Robust Multi-View Spectral Clustering via Low-Rank and Sparse Decomposition[C]∥28th AAAI Conference on Artificial Intelligence.2014:2149-2155.
[28]CHAUDHURI K,KAKADE S M,LIVESCU K,et al.Multi-view clustering via canonical correlation analysis[C]∥Procee-dings of the 26th Annual International Conference on Machine Learning.ACM,2009:129-136.
[29]XIA T,TAO D,MEI T,et al.Multiview spectral embedding[J].IEEE Transactions on Systems Man and Cybernetics Part B,2010,40(6):1438-1446.
[30]GREENE D,CUNNINGHAM P.A matrix factorization Ap-proach for integrating multiple data views[C]∥Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases.2009:423-438.
[31]XU C,TAO D,XU C.A survey on multi-view learning.arXivpreprint arXiv:1304.5634,2013.
[32]SUN S.A survey of multi-view machine learning[J].NeuralComputing and Applications,2013,23(7/8):2031-2038.
[33]ZHANG M L,ZHOU Z H.A review on multi-label learning algorithms[J].IEEE Transactions on Knowledge and Data Engineering,2014,26(8):1819-1837.
[34]BLEI D M,NG A Y,JORDAN M I.Latent dirichlet allocation[J].Journal of Jachine Learning Research,2003,3(1):993-1022.
[1] 丁锋, 孙晓.
基于注意力机制和BiLSTM-CRF的消极情绪意见目标抽取
Negative-emotion Opinion Target Extraction Based on Attention and BiLSTM-CRF
计算机科学, 2022, 49(2): 223-230. https://doi.org/10.11896/jsjkx.210100046
[2] 袁景凌, 丁远远, 盛德明, 李琳.
基于视觉方面注意力的图像文本情感分析模型
Image-Text Sentiment Analysis Model Based on Visual Aspect Attention
计算机科学, 2022, 49(1): 219-224. https://doi.org/10.11896/jsjkx.201000074
[3] 胡艳丽, 童谭骞, 张啸宇, 彭娟.
融入自注意力机制的深度学习情感分析方法
Self-attention-based BGRU and CNN for Sentiment Analysis
计算机科学, 2022, 49(1): 252-258. https://doi.org/10.11896/jsjkx.210600063
[4] 戴宏亮, 钟国金, 游志铭, 戴宏明.
基于Spark的舆情情感大数据分析集成方法
Public Opinion Sentiment Big Data Analysis Ensemble Method Based on Spark
计算机科学, 2021, 48(9): 118-124. https://doi.org/10.11896/jsjkx.210400280
[5] 张瑾, 段利国, 李爱萍, 郝晓燕.
基于注意力与门控机制相结合的细粒度情感分析
Fine-grained Sentiment Analysis Based on Combination of Attention and Gated Mechanism
计算机科学, 2021, 48(8): 226-233. https://doi.org/10.11896/jsjkx.200700058
[6] 史伟, 付月.
考虑语境的微博短文本挖掘:情感分析的方法
Microblog Short Text Mining Considering Context:A Method of Sentiment Analysis
计算机科学, 2021, 48(6A): 158-164. https://doi.org/10.11896/jsjkx.210200089
[7] 潘芳, 张会兵, 董俊超, 首照宇.
基于高效Transformer的中文在线课程评论方面情感分析
Aspect Sentiment Analysis of Chinese Online Course Review Based on Efficient Transformer
计算机科学, 2021, 48(6A): 264-269. https://doi.org/10.11896/jsjkx.200800116
[8] 张明阳, 王刚, 彭起, 张岩峰.
学术论文公开评审平台数据分析
Data Analysis of OpenReview
计算机科学, 2021, 48(6): 63-70. https://doi.org/10.11896/jsjkx.200500138
[9] 尹久, 池凯凯, 宦若虹.
基于ATT-DGRU的文本方面级别情感分析
Aspect-level Sentiment Analysis of Text Based on ATT-DGRU
计算机科学, 2021, 48(5): 217-224. https://doi.org/10.11896/jsjkx.200500076
[10] 李建兰, 潘岳, 李小聪, 刘子维, 王天宇.
基于CiteSpace的中文评论文本研究现状与趋势分析
Chinese Commentary Text Research Status and Trend Analysis Based on CiteSpace
计算机科学, 2021, 48(11A): 17-21. https://doi.org/10.11896/jsjkx.210300172
[11] 杨青, 张亚文, 朱丽, 吴涛.
基于注意力机制和BiGRU融合的文本情感分析
Text Sentiment Analysis Based on Fusion of Attention Mechanism and BiGRU
计算机科学, 2021, 48(11): 307-311. https://doi.org/10.11896/jsjkx.201000075
[12] 徐琳宏, 刘鑫, 原伟, 祁瑞华.
俄语多模态情感语料库的构建及应用
Construction and Application of Russian Multimodal Emotion Corpus
计算机科学, 2021, 48(11): 312-318. https://doi.org/10.11896/jsjkx.200900088
[13] 张帆, 贺文琪, 姬红兵, 李丹萍, 王磊.
基于块对角化表示的多视角字典对学习
Multi-view Dictionary-pair Learning Based on Block-diagonal Representation
计算机科学, 2021, 48(1): 233-240. https://doi.org/10.11896/jsjkx.200800211
[14] 张严, 李天瑞.
面向评论的方面级情感分析综述
Review of Comment-oriented Aspect-based Sentiment Analysis
计算机科学, 2020, 47(6): 194-200. https://doi.org/10.11896/jsjkx.200200127
[15] 王青松, 姜富山, 李菲.
大数据环境下基于关联规则的多标签学习算法
Multi-label Learning Algorithm Based on Association Rules in Big Data Environment
计算机科学, 2020, 47(5): 90-95. https://doi.org/10.11896/jsjkx.190300150
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!