|本期目录/Table of Contents|

[1]李俊杰,宗成庆*.融合用户信息和评价对象信息的文本情感分类[J].厦门大学学报(自然科学版),2018,57(06):876-883.[doi:10.6043/j.issn.0438-0479.201807004]
 LI Junjie,ZONG Chengqing*.Document-level Sentiment Classification Considering User Information and Aspect Information[J].Journal of Xiamen University(Natural Science),2018,57(06):876-883.[doi:10.6043/j.issn.0438-0479.201807004]
点击复制

融合用户信息和评价对象信息的文本情感分类(PDF/HTML)
分享到:

《厦门大学学报(自然科学版)》[ISSN:0438-0479/CN:35-1070/N]

卷:
57卷
期数:
2018年06期
页码:
876-883
栏目:
自然语言处理
出版日期:
2018-11-28

文章信息/Info

Title:
Document-level Sentiment Classification Considering User Information and Aspect Information
文章编号:
0438-0479(2018)06-0876-08
作者:
李俊杰12宗成庆123*
1.中国科学院自动化研究所,模式识别国家重点实验室 北京 100190; 2.中国科学院大学计算机与控制学院,北京 100190; 3.中国科学院脑科学与智能技术卓越创新中心,北京 100190
Author(s):
LI Junjie12ZONG Chengqing123*
1.National Laboratory of Pattern Recognition,Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China; 2.School of Computer and Control Engineering,University of Chinese Academy of Sciences,Beijing 100190,China; 3.Center for Excellence i
关键词:
情感分类 用户信息 深度学习
Keywords:
sentiment classification user information deep learning
分类号:
TP 391
DOI:
10.6043/j.issn.0438-0479.201807004
文献标志码:
A
摘要:
文档级别情感分类的目的在于预测用户对评论文本的情感倾向.目前大部分工作只关注于文档的内容而忽视了用户信息和评价对象信息.事实上,不同的用户在表达情感时选词存在着差异,并且对同一产品不同属性的关注度也会有所不同; 不同的词汇在描述不同的评价对象时,也会有着不同的情感倾向性.为了能同时考虑用户和评价对象,提出了一个基于用户和评价对象的层次化注意力网络(hierarchical user aspect attention networks,HUAAN)模型.该模型首先用一个层次化的结构编码各类信息(包括词汇、句子、评价对象、文档),然后引入基于用户和评价对象的注意力机制来建模这两类信息.为了验证HUAAN模型的有效性,在两个真实的数据集上进行实验,结果表明在融入这两类信息之后,HUAAN在同等条件下比NSC+UPA系统的准确率高.
Abstract:
Document-level sentiment classification aims to infer user’s sentiment polarity in a review.However,most of existing methods only focus on text information and ignore user information and aspect information.Different users may use different words to express their opinions and pay their attentions to different aspects about a product.Words describing different aspects may induce different sentiment polarities.These two kinds of information are helpful to sentiment classification.To consider these two kinds of information,we propose a model called hierarchical user aspect attention networks(HUAAN),which can encode different kinds of information(word,sentence,aspect,document)in a hierarchical structure and import the user-and-aspect-attention mechanism to model user information and aspect information.Empirical results on two real-world document-level review datasets show that our model obtains the best classification in the same condition.The accuracy rate of sentiment classification is higher than the system of NSC+UPA-pro.

参考文献/References:

[1] 宗成庆.统计自然语言处理[M].北京:清华大学出版社,2013:430-431.
[2] PANG B,LEE L,VAITHYANATHAN S.Thumbs up? Sentiment classification using machine learning techniques[C]∥Proceedings of the International Conference on Empirical Methods in Natural Language Processing.Philadelphia:ACL,2002:79-86.
[3] XIA R,ZONG C Q,LI S S.Ensemble of feature sets and classification algorithms for sentiment classification[J].Information Sciences,2011,181(6):1138-1152.
[4] WANG S D,MANNING C D.Baselines and bigrams:simple,good sentiment and topic classification[C]∥Proceedings of the Annual Meeting of the Association for Computational Linguistics.Jeju Island:ACL,2012:90-94.
[5] LI S S,XUE Y X,WANG Z Q,et al.Active learning for cross-domain sentiment classification[C]∥Proceedings of the International Joint Conference on Artificial Intelligence.Washington DC:IEEE,2013:2127-2133.
[6] SOCHER R,PENNINGTON J,HUANG E,et al.Semi-supervised recursive autoencoders for predicting sentiment distributions[C]∥Proceedings of the International Conference on Empirical Methods in Natural Language Processing.Scotland:ACL,2011:151-161.
[7] SOCHER R,PERELYGIN A,WU J Y,et al.Recursive deep models for semantic compositionality over a sentiment treebank[C]∥Proceedings of the International Conference on Empirical Methods in Natural Language Processing.Seattle:ACL,2013:1631-1642.
[8] TANG D Y,WEI F R,YANG N,et al.Learning sentiment-specific word embedding for twitter sentiment classification[C]∥Proceedings the Annual Meeting of the Association for Computational Linguistics.Maryland:ACL,2014:1555-1565.
[9] TANG D Y,QIN B,LIU T.Document modeling with gated recurrent neural network for sentiment classification[C]∥Proceedings of the international conference on Empirical Methods in Natural Language Processing.Lisbon:ACL,2015:1422-1432.
[10] TANG D Y,QIN B,LIU T.Learning semantic representations of users and products for document level sentiment classification[C]∥Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing.Beijing:ACL,2015:1014-1023.
[11] CHEN H M,SUN M S,TU C C,et al.Neural sentiment classification with user and product attention[C]∥Proceedings of the International Conference on Empirical Methods in Natural Language Processing.Texas:ACL,2016:1650-1659.
[12] DOU Z Y.Capturing user and product information for document level sentiment analysis with deep memory network[C]∥Proceedings of the International Conference on Empirical Methods in Natural Language Processing.Copenhagen:ACL,2017:532-537.
[13] HU M Q,LIU B.Mining and summarizing customer reviews[C]∥Proceedings of the International Conference on Knowledge Discovery and Data Mining.Seattle:ACM,2004:168-177.
[14] HU M Q,LIU B.Mining opinion features in customer reviews[C]∥Proceedings of the International Joint Conference on Artificial Intelligence.California:IEEE,2004:755-760.
[15] HOCHREITER S,SCHMIHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780.
[16] TANG D Y,QIN B,LIU T.Aspect level sentiment classification with deep memory network[C]∥Proceedings of the International Conference on Empirical Methods in Natural Language Processing.Texas:ACL,2016:214-224.
[17] WANG Y Q,HUANG M L,ZHU X Y,et al.Attention-based LSTM for aspect-level sentiment classification[C]∥Proceedings of the International Conference on Empirical Methods in Natural Language Processing.Texas:ACL,2016:606-615.
[18] MANNING C D,SURDEANU M,BAUER J,et al.The stanford corenlp natural language processing toolkit[C]∥Proceedings of the Annual Meeting of the Association for Computational Linguistics:System Demonstrations.Maryland:ACL,2014:55-60.
[19] YANG Z C,YANG D Y,DYER C,et al.Hierarchical attention networks for document classification[C]∥Proceedings of Annual Conference of the North American Chapter of the Association for Computational Linguistics.California:ACL,2016:1480-1489.
[20] PANG B,LEE L.Opinion mining and sentiment analysis[J].Foundations and Trends in Information Retrieval,2008,2(1/2):1-135.
[21] LIU B.Sentiment analysis and opinion mining[J].Synthesis Lectures on Human Language Technologies,2012,5(1):1-167.
[22] SOCHER R,HUVAL B,MANNING C D,et al.Semantic compositionality through recursive matrix-vector spaces[C]∥Proceedings of the International Conference on Empirical Methods in Natural Language Processing.Jeju Island:ACL,2012:1201-1211.
[23] KIM Y.Convolutional neural networks for sentence classification[C]∥Proceedings of the International Conference on Empirical Methods in Natural Language Processing.Doha:ACL,2014:1746-1751.
[24] BHATIA P,JI Y F,EISENSTEIN J.Better document-level sentiment analysis from RST discourse parsing[C]∥Proceedings of the International Conference on Empirical Methods in Natural Language Processing.Lisbon:ACL,2015:2212-2218.
[25] LI J J,YANG H T,ZONG C Q.Sentiment classification of social media text considering user attributes[C]∥Proceedings of the Conference on Natural Language Processing and Chinese Computing.Kunming:CCF,2016:583-594.
[26] GUI L,ZHOU Y,XU R F,et al.Learning representations from heterogeneous network for sentiment classification of product reviews[J].Knowledge-Based Systems,2017,124:34-45.
[27] AMPLAYO R K,KIM J,SUNG S,et al.Cold-start aware user and product attention for sentiment classification[C]∥Proceedings of the Annual Meeting of the Association for Computational Linguistics.Melbourne:ACL,2018:2535-2544.
[28] WU Z,DAI X Y,YIN C Y,et al.Improving review representations with user attention and product attention for sentiment classification[C]∥Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence.Louisiana:IEEE,2018:5989-5996.

备注/Memo

备注/Memo:
收稿日期:2018-07-02 录用日期:2018-09-14
基金项目:国家自然科学基金(61333018)
*通信作者:cqzong@nlpr.ia.ac.cn
引文格式:李俊杰,宗成庆.融合用户信息和评价对象信息的文本情感分类[J].厦门大学学报(自然科学版),2018,57(6):876-883.
Citation:LI J J,ZONG C Q.Document-level sentiment classification considering user information and aspect information[J].J Xiamen Univ Nat Sci,2018,57(6):876-883.(in Chinese)
更新日期/Last Update: 1900-01-01