摘要
随着在线评论信息数量的快速增长与应用的不断扩展,评论挖掘研究得到学术界的持续关注。当前的评论挖掘任务对属性的全面性、细粒度等要求越来越高,而多数现有研究方法主要关注评价对象主要属性的抽取。尽可能地发现评价对象的全部用户关注属性、并以细粒度方式表述属性,是一项有意义的工作。本文提出一种细粒度属性抽取方法,旨在全面、快速地抽取产品属性。本文首先利用高频名词构建候选属性词;然后通过深度学习构建候选属性词向量,在此基础上完成候选属性的聚类,得到聚类后的候选属性词集;最后对候选属性词集进行噪音过滤,得到细粒度产品属性集。在饮食、手机、图书等三个领域评论语料上的实验结果表明,相对于基于种子词的方法、基于结合人工的LDA方法及基于情感词的方法,本文方法能够更加全面地发现评价对象属性,并且能够给出细粒度的属性。
With the rapid development of online reviews and related applications, review mining has been given sustained attention in academia. Currently,aspect mining has higher requirements for comprehensiveness and fine granularity. However, most existing methods focus on mining essential product aspects. Locating all aspects concerned by users and describing aspects in a fine-grained manner is a meaningful work. Hence, in this paper, we propose a fine-grained aspect extraction method, which attempts to extract product aspects comprehensively and effectively. Specifically, we first extract candidate aspects based on frequent nouns, and then, using deep learning, we construct candidate aspect vectors for clustering synonymous aspects. Finally, we obtain aspect sets by filtering the noise in candidate aspect sets. Experimental results on a corpus of dietary, mobile phones, and books, show that,compared with the seed words-based method, LDA-based method, and sentiment words-based method, our method can comprehensively extract opinion target aspects and identify more fine-grained aspects.
引文
[1]Liu B.Sentiment analysis and opinion mining[J].Synthesis Lectures on Human Language Technologies,2012,5(1):1-167.
[2]Hu M Q,Liu B.Mining and summarizing customer reviews[C]//Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York:ACM Press,2004:168-177.
[3]Moghaddam S,Ester M.Opinion digger:an unsupervised opinion miner from unstructured product reviews[C]//Proceedings of the ACM Conference on Information and Knowledge Management.New York:ACM Press,2010:1825-1828.
[4]Bagheri A,Saraee M,de Jong F.An unsupervised aspect detection model for sentiment analysis of reviews[C]//Metais E,Meziane F,Saraee M,et al(eds).Natural Language Processing and Information Systems.NLDB 2013:Lecture Notes in Computer Science.Heidelberg:Springer Berlin,2013,7934:140-151.
[5]Mukherjee A,Liu B.Aspect extraction through semi-supervised modeling[C]//Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics.Stroudsburg:Association for Computational Linguistics,2012,1:339-348.
[6]Ma B,Zhang D,Yan Z,et al.An LDA and synonym lexicon based approach to product feature extraction from online consumer product reviews[J].Journal of Electronic Commerce Research,2013,14(4):304-314.
[7]Poria S,Cambria E,Ku L.A rule-based approach to aspect extraction from product reviews[C]//Proceedings of the 2nd Workshop on Natural Language Processing for Social Media,2014:28-37.
[8]Hai Z,Chang K Y,Kim J J,et al.Identifying features in opinion mining via intrinsic and extrinsic domain relevance[J].IEEE Transactions on Knowledge&Data Engineering,2014,26(3):623-634.
[9]Li Y,Wang H,Qin Z,et al.Confidence estimation and reputation analysis in aspect extraction[C]//Proceedings of the International Conference on Pattern Recognition.Institute of Electrical and Electronics Engineers,2014:3612-3617.
[10]Li Y,Qin Z,Xu W R,et al.A holistic model of mining product aspects and associated sentiments from online reviews[J].Multimedia Tools and Applications,2015,74(23):10177-10194.
[11]Maharani W,Widyantoro D H,Khodra M L.Learning-based aspect identification in customer review products[C]//Proceedings of the International Conference on Electrical Engineering and Informatics,2015:71-76.
[12]Liu Q,Gao Z Q,Liu B,et al.Automated rule selection for aspect extraction in opinion mining[C]//Proceedings of the 24th International Conference on Artificial Intelligence.Palo Alto:AAAI Press,2015:1291-1297.
[13]Liu K,Xu L H,Liu Y,et al.Opinion target extraction using partially-supervised word alignment model[C]//Proceedings of theTwenty-Third International Joint Conference on Artificial Intelligence.Palo Alto:AAAI Press,2013:2134-2140.
[14]Li D,Chen G,Li Y,et al.Mining consumer's opinion target based on translation model and word representation[C]//Proceedings of the 11th International Computer Conference on Wavelet Active Media Technology and Information Processing,2015:97-101.
[15]Fellbaum C,Miller G.WordNet:an electronic lexical database[M].Cambridge:MIT Press,1998.
[16]Samha A K,Li Y F,Zhang J L.Aspect-based opinion extraction from customer reviews[J].International Journal of Computer Science&Information Technology,2014,6(3):149-160.
[17]Bancken W,Alfarone D,Davis J.Automatically detecting and rating product aspects from textual customer reviews[C]//Proceedings of the 1st International Workshop on Interactions between Data Mining and Natural Language Processing at ECML/PKDD,2014,1202:1-16.
[18]Chen Z Y,Mukherjee A,Liu B.Aspect extraction with automated prior knowledge learning[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics,2014,1:347-358.
[19]Mukherjee A,Liu B.Aspect extraction through semi-supervised modeling[C]//Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics.Stroudsburg:Association for Computational Linguistics,2012,1:339-348.
[20]Zhao L,Huang M L,Chen H Q,et al.Clustering aspect-related phrases by leveraging sentiment distribution consistency[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing,2014:1614-1623.
[21]Suleman K,Vechtomova O.Discovering aspects of online consumer reviews[J].Journal of Information Science,2015,42(4):492-506.
[22]Zhao L,Huang M L,Sun J S,et al.Sentiment extraction by leveraging aspect-opinion association structure[C]//Proceedings of the 24th ACM International Conference on Information and Knowledge Management.New York:ACM Press,2015:343-352.
[23]Wu Y B,Zhang Q,Huang X J,et al.Phrase dependency parsing for opinion mining[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing.Stroudsburg:Association for Computational Linguistics,2009,3:1533-1541.
[24]Hinton G E.Distributed representations[M].Pittsburgh:Carnegie Mellon University,1984.
[25]Mikolov T,Sutskever I,Chen K,et al.Distributed representations of words and phrases and their compositionality[J].Advances in Neural Information Processing Systems,2013,26(3):111-119.
[26]Salton G,Wong A,Yang C S.A vector space model for automatic indexing[J].Communications of the ACM,1975,18(11):613-620.
[27]Frey B J,Dueck D.Clustering by passing messages between data points[J].Science,2007,315(5814):972-976.
[28]Blei D M,Ng A Y,Jordan M I.Latent dirichlet allocation[J].Journal of Machine Learning Research,2003,3:993-1022.
[29]Salton G,McGill M J.Introduction to modern information retrieval[M].New York:McGraw-Hill,1986:305-306.
(1)http://www.ansj.org/
(2)http://word2vec.googlecode.com/svn/trunk/
(1)http://www.keenage.com/
(2)http://www.datatang.com/data/44317