A Semi-supervised Method for Phrase-Level Sentiment Analysis
Odbal, WANG Zengfu
Nuclear Environment Telerobot Laboratory, Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230031 Department of Automation, University of Science and Technology of China, Hefei 230027
Abstract：The existing methods for sentiment analysis can not dig more complex linguistic phenomena in emotional expression and they encounter the challenge of sparse features. An innovative semi-supervised phrase-level sentiment analysis method based on semantic space model is proposed. Firstly, the problem of word representation in semantic space is discussed and word-level semantic distribution computing methods based on dependency grammar semantic space model are proposed, and the computational procedure is completed by using unsupervised method. Secondly, the problems of phrase recognition and representation are discussed and nonlinear combinations of word-level semantic distribution are used to represent the multi-word structures. Finally, a neutral network algorithm is used to design the phrase-level sentiment analysis system based on word level semantic distribution and phrasal structure representation. Experimental results on real Chinese corpora show the expected recognition accuracy of the model.
[1] PANG B, LEE L, VAITHYANATHAN S. Thumbs Up? Sentiment Classification Using Machine Learning Techniques // Proc of the Conference on Empirical Methods in Natural Language Processing. Philadelphia, USA, 2002: 79-86. [2] DAVE K, LAWRENCE S, PENNOCK D M. Mining the Peanut Gallery: Opinion Extraction and Semantic Classification of Product Reviews // Proc of the 12th International World Wide Web Conference. Budapest, Hungary, 2003: 519-528. [3] NG V, DASGUPTA S, NIAZ ARIFIN S M. Examining the Role of Linguistic Knowledge Sources in the Automatic Identification and Classification of Reviews // Proc of the 21st International Confe-rence on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics. Sydney, Australia, 2006: 611-618. [4] IKEDA D, TAKAMURA H, RATINOV L A, et al. Learning to Shift the Polarity of Words for Sentiment Classification // Proc of the 3rd International Joint Conference on Natural Language Proce-ssing. Hyderabad, India, 2008, I: 296-303. [5] MATSUMOTO S, TAKAMURA H, OKUMURA M. Sentiment Cla-ssification Using Word Sub-sequences and Dependency Sub-trees // Proc of the 9th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining. Hanoi, Vietnam, 2005: 301-311. [6] MCDONALD R T, HANNAN K, NEYLON T, et al. Structured Models for Fine-to-Coarse Sentiment Analysis // Proc of the 45th Annual Meeting of the Association for Computational Linguistics. Prague, Czech Republic, 2007: 432-439. [7] WILSON T, WIEBE J, HOFFMANN P. Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis // Proc of the Human Language Technology Conference and the Conference on Empirical Methods in Natural Language Processing. Vancouver, Canada, 2005: 347-354. [8] WILSON T, WIEBE J, HOFFMANN P. Recognizing Contextual Polarity: An Exploration of Features for Phrase-Level Sentiment Analysis. Association for Computational Linguistics, 2009, 35(3): 399-433. [9] TAKAMURA H, INUI T, OKUMURA M. Latent Variables Models for Semantic Orientation of Phrases [2015-06-30]. [EB/OL]. http://www.aclweb.org/anthology/E06-1026.pdf. [10] TAKAMURA H, INUI T, Okumura M. Extracting Semantic Orientations of Phrases from Dictionary // Proc of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Rochester, USA, 2007: 292-299. [11] BRECK E, CHOI Y J, CARDIE C. Identifying Expressions of Opi-nion in Context // Proc of the 20th International Joint Conference on Artificial Intelligence. Hyderabad, India, 2007: 2683-2688. [12] NAKAGAWA T, INUI K, KUROHASHI S. Dependency Tree-based Sentiment Classification Using CRFs with Hidden Variables // Proc of the Conference of the North American Chapter of the Association of Computational Linguistics: Human Language Technologies. Los Angeles, USA, 2010: 786-794. [13] CHOI Y J, CARDIE C. Learning with Compositional Semantics as Structural Inference for Subsentential Sentiment Analysis // Proc of the Conference on Empirical Methods in Natural Language Proce-ssing. Honolulu, USA, 2008: 793-801. [14] YESSENALINA A, CARDIE C. Compositional Matrix-Space Mo-dels for Sentiment Analysis // Proc of the Conference on Empirical Methods in Natural Language Processing. Edinburgh, UK, 2011: 172-182. [15] SOCHER R, PENNINGTON J, HUANG E H, et al. Semi-supervised Recursive Autoencoders for Predicting Sentiment Distributions // Proc of the Conference on Empirical Methods in Natural Language Processing. Edinburgh, UK, 2011: 151-161. [16] SOCHER R, HUVAL B, MANNING C D, et al. Semantic Compositionality through Recursive Matrix-Vector Spaces // Proc of the Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Jeju Island, Republic of Korea, 2012: 1201-1211. [17] XU L H, LIU K, LAI S W, et al. Product Feature Mining: Semantic Clues versus Syntactic Constituents // Proc of the 52nd Annual Meeting of the Association for Computational Linguistics. Ba-ltimore, USA, 2014, I: 336-346. [18] 刘鸿宇,赵妍妍,秦 兵,等.评价对象抽取及其倾向性分析.中文信息学报. 2010, 24(1): 84-88. (LIU H Y, ZHAO Y Y, QIN B, et al. Comment Target Extraction and Sentiment Classification. Journal of Chinese Information Processing, 2010, 24(1): 84-88.) [19] HUANG M L, YE B R, WANG Y C, et al. New Word Detection for Sentiment Analysis // Proc of the 52nd Annual Meeting of the Association for Computational Linguistics. Baltimore, USA, 2014, I: 531-541. [20] LIU K, XU L H, ZHAO J. Extracting Opinion Targets and Opinion Words from Online Reviews with Graph Co-ranking // Proc of the 52nd Annual Meeting of the Association for Computational Linguistics. Baltimore, USA, 2014, I: 314-324. [21] CHEN Q, LI W J, LEI Y, et al. Learning to Adapt Credible Knowledge in Cross-Lingual Sentiment Analysis // Proc of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Beijing, China, 2015, I: 419-429. [22] ZHOU H W, CHEN L, SHI F L, et al. Learning Bilingual Sentiment Word Embeddings for Cross-Language Sentiment Classification // Proc of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Beijing, China, 2015, I: 430-440. [23] LOWE W. Towards a Theory of Semantic Space // Proc of the 6th Neural Computation and Psychology Workshop. Liege, Belgium, 2001: 576-581. [24] BENGIO Y, DUCHARME R, VINCENT P, et al. A Neural Pro-babilistic Language Model. Journal of Machine Learning Research, 2003, 3: 1137-1155. [25] MITCHELL J, LAPATA M. Vector-Based Models of Semantic Composition // Proc of the 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Columbus, USA, 2008: 236-244.
2016, Vol. 29 
