Crucial data like product features and opinions are mined from online reviews. The obtained opinions are further analyzed for orientations. These orientations that are positive, negative or neutral are counted to determine the sentiment of the feature. The product recommendations performed by using the sentiments lead to a problem called “customer churn”. This is due to the tide of sentiment change. The reviewer intention on the product feature is important in finalizing the recommended list of product cases. In order to carry out this, the statistical intentions are calculated. The product cases are generated for a product by using these calculated intentions. The statistical intentions of the common features are stabilized to uncover the finalized features at the time of product similarity calculation. This “intent-to-opine” way of product recommendations addresses the problem of customer churn in the long run.

Customer Reviews, Product Features, Sentiments, Customer Churn, Intentions, Product Recommendations, Case Based Reasoning

[1] Dong, Ruihai, et al. "Opinionated product recommendation." International Conference on Case-Based Reasoning. Springer Berlin Heidelberg, 2013.
[2] http://www.infosysblogs.com/data-analytics/2013/12/_my_personal_experience_of.html. Accessed on 10-04-2017.
[3] Liu, Yang, et al. "Riding the tide of sentiment change: sentiment analysis with evolving online reviews." World Wide Web 16.4 (2013): 477-496.
[4] Carlos, Cohan Sujay, and Madhulika Yalamanchi. "Intention Analysis for Sales, Marketing and Customer Service." COLING (Demos). 2012.
[5] Turney, Peter D., and Michael L. Littman. "Measuring praise and criticism: Inference of semantic orientation from association." ACM Transactions on Information Systems (TOIS) 21.4 (2003): 315-346.
[6] http://www.aiaioo.com/whitepapers/intention_analysis_use_cases.pdf. Accessed on 10-04-2017.
[7] Resnick, Paul, et al. "GroupLens: an open architecture for collaborative filtering of netnews." Proceedings of the 1994 ACM conference on Computer supported cooperative work. ACM, 1994.
[8] Stavrianou, Anna, and Caroline Brun. "Expert Recommendations Based on Opinion Mining of User‐Generated Product Reviews." Computational Intelligence 31.1 (2015): 165-183.
[9] Lang, Ken. "Newsweeder: Learning to filter netnews." Proceedings of the 12th international conference on machine learning. 1995.
[10] Zhou, Jia, Tiejian Luo, and Fuxing Cheng. "Modeling learners and contents in academic-oriented recommendation framework." Dependable, Autonomic and Secure Computing (DASC), 2011 IEEE Ninth International Conference on. IEEE, 2011.
[11] Kolodner, Janet. Case-based reasoning. Morgan Kaufmann, 2014.
[12] Burke, Robin D., Kristian J. Hammond, and B. C. Yound. "The FindMe approach to assisted browsing." IEEE Expert 12.4 (1997): 32-40.
[13] Holland, Stefan, Martin Ester, and Werner Kießling. "Preference mining: A novel approach on mining user preferences for personalized applications." European Conference on Principles of Data Mining and Knowledge Discovery. Springer Berlin Heidelberg, 2003.
[14] Chen, Guanliang, and Li Chen. "Recommendation based on contextual opinions." International Conference on User Modeling, Adaptation, and Personalization. Springer International Publishing, 2014.
[15] Gurini, Davide Feltoni, et al. "Analysis of sentiment communities in online networks." Proceedings of the International Workshop on Social Personalization & Search, co-located at SIGIR. 2015.
[16] Li, Xiu, Huimin Wang, and Xinwei Yan. "Accurate recommendation based on opinion mining." Genetic and Evolutionary Computing. Springer International Publishing, 2015. 399-408.
[17] Dong, Ruihai, et al. "Combining similarity and sentiment in opinion mining for product recommendation." Journal of Intelligent Information Systems 46.2 (2016): 285-312.
[18] Toutanova, Kristina, and Christopher D. Manning. "Enriching the knowledge sources used in a maximum entropy part-of-speech tagger." Proceedings of the 2000 Joint SIGDAT conference on Empirical methods in natural language processing and very large corpora: held in conjunction with the 38th Annual Meeting of the Association for Computational Linguistics-Volume 13. Association for Computational Linguistics, 2000.
[19] Manning, Christopher. "Part-of-speech tagging from 97% to 100%: is it time for some linguistics?." Computational Linguistics and Intelligent Text Processing (2011): 171-189.
[20] Liu, Bing. Web data mining: exploring hyperlinks, contents, and usage data. Springer Science & Business Media, 2007.
[21] Christiane Fellbaum (1998, ed.) WordNet: An Electronic Lexical Database. Cambridge, MA: MIT Press.
[22] Cambria, Erik, et al. "SenticNet: A Publicly Available Semantic Resource for Opinion Mining." AAAI fall symposium: commonsense knowledge. Vol. 10. No. 0. 2010.
[23] Lafferty, John, Andrew McCallum, and Fernando Pereira. "Conditional random fields: Probabilistic models for segmenting and labeling sequence data." Proceedings of the eighteenth international conference on machine learning, ICML. Vol. 1. 2001.
[24] Poria, Soujanya, et al. "A rule-based approach to aspect extraction from product reviews." Proceedings of the second workshop on natural language processing for social media (SocialNLP). 2014.
[25] Hu, Minqing, and Bing Liu. "Mining and summarizing customer reviews." Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 2004.
[26] Huang, Anna. "Similarity measures for text document clustering." Proceedings of the sixth new zealand computer science research student conference (NZCSRSC2008), Christchurch, New Zealand. 2008.
[27] http://gadgets.ndtv.com/samsung-galaxy-j7-prime-3735-vs-oppo-f1-plus-3414-vs-apple-iphone-6s-plus-2955 . Accessed on 10-04-2017.
[28] Wang, Wei, and Hongwei Wang. "Opinion-enhanced collaborative filtering for recommender systems through sentiment analysis." New Review of Hypermedia and Multimedia 21.3-4 (2015): 278-300.