Automatic Extraction of Features and Opinion-Oriented Sentences from Customer Reviews

Authors: Khairullah Khan, Baharum B. Baharudin, Aurangzeb Khan, Fazal_e_Malik

Abstract:

Opinion extraction about products from customer reviews is becoming an interesting area of research. Customer reviews about products are nowadays available from blogs and review sites. Also tools are being developed for extraction of opinion from these reviews to help the user as well merchants to track the most suitable choice of product. Therefore efficient method and techniques are needed to extract opinions from review and blogs. As reviews of products mostly contains discussion about the features, functions and services, therefore, efficient techniques are required to extract user comments about the desired features, functions and services. In this paper we have proposed a novel idea to find features of product from user review in an efficient way. Our focus in this paper is to get the features and opinion-oriented words about products from text through auxiliary verbs (AV) {is, was, are, were, has, have, had}. From the results of our experiments we found that 82% of features and 85% of opinion-oriented sentences include AVs. Thus these AVs are good indicators of features and opinion orientation in customer reviews.

Keywords: Classification, Customer Reviews, Helping Verbs, Opinion Mining.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1074753

References:

[1] Bo Pang and Lillian Lee, "Opinion Mining and Sentiment Analysis", Foundations and Trends in Information Retrieval Vol. 2, Nos. 1-2 (2008) 1-135 2008, 2008.
[2] QI Su et al., Mining Feature-based Opinion Expressions by Mutual information Approach, International Journal of Computer Processing of Oriental Languages, 2007
[3] comScore, "Online consumer-generated reviews have significant impact on online purchase behavior," Press Release, http://www.comscore.com/press/release.asp?press=1928, November 2007.
[4] ] Hu and Bing Liu, "Mining Opinion Features in Customer Reviews", American Association for Artificial Intelligence 2004, 2004.
[5] Changli Zhang1 et al., "Sentiment Classification for Chinese Reviews Using Machine Learning Methods Based on String Kernel", Third 2008 International Conference on Convergence and Hybrid Information Technology, 2008.
[6] Carlo Strapparava, Rada Mihalcea, "Learning to Identify Emotions in Text", SAC-08 March 1620, 2008, 2008.
[7] Nitin Jindal and Bing Liu, "Mining Comparative Sentences and Relations", American Association for Artificial Intelligence, www.aaai.org., 2006.
[8] Ahmed Abbas, etl. "Sentiment Analysis in Multiple Languages: Feature Selection for Opinion Classification in Web Forums" ACM Transactions on Information Systems, Vol. 26, No. 3, Article 12, 2008.
[9] Gamgarn Somprasertsri et al., Automatic product feature extraction from online product reviews using maximum entropy with lexical and syntactic features, in Proc. IRI 2008, 2008.
[10] Stefano Baccianella, et al., "Multi-facet rating of product reviews", ECIR 2009, LNCS 5478, pp. 461-472, 2009.
[11] A.M. popescu and O. Etzioni, extracting product features and opinion from reviews, in Proc. HLT-EMNLP 2005, 2005.
[12] M.Q. Hu and B. Liu Mining and summarizing customer reviews, in Proc. KDD(2004), 2004.
[13] N. Kobayashi, K. et al., Collecting evaluative expressions for opinion extraction, in Proc. IJCNLP(2004), 2004.
[14] V. Hatzivassiloglou and K. McKeown, "Predicting the semantic orientation of adjectives," in Proceedings of the Joint ACL/EACL Conference, pp. 174-181, 1997.
[15] Livia Polanyi and Annie Zaenen, "Contextual valence shifter", Computing Attitude and Affect in Text: Theory and Applications chapter 1, pages 1-10. Springer, 2006.
[16] Changli Zhang et al., "Sentiment Classification for Chinese Reviews Using Machine Learning Methods based on String Kernel", International on Convergence and Hybrid Information Technology, 2008.
[17] Xiaowen Ding and Bing Liu, "The Utility of Linguistic Rules in Opinion Mining", SIGIR-07, Amsterdam, Netherlands, 2007.
[18] Alina Andreevskaia and Sabine Bergler, "Mining Word-Net for fuzzy sentiment: Sentiment tag extraction from WordNet glosses", In Proceedings of the 11th Conference of the European Chapter of the Association for Computational Linguistics (EACL-06), pages 209-216, Trento, IT. 2006