OPINION EXTRACTION FROM ONLINE REVIEWS

S. VIDHYA, C. VIDHYA ABINAYA, R. VISUTHA, P.V. KAVITHA

Abstract


Now a days online shopping is mostly preferred by customers rather than going to the shops. So before they buy a product, they will refer to the previous customer’s reviews by navigating to the review page. Opinion mining eases this task by classifying the customer reviews. This paper proposes a novel approach based on the partially supervised word alignment model to extract the opinion relations using constrained Hill Climbing Algorithm. Finally, using these relations, the number of positive reviews and the number of negative reviews are classified. Compared to previous method which is based on the nearest neighbor rules that cannot support large sized corpus, our model captures opinion relations accurately, especially for long sized corpus. Compared to Syntax – based method, our model effectively ignores the parsing errors when dealing with informal text.

Keywords


Opinion Mining, Opinion Target Extraction, Opinion Words Extraction.

Full Text:

PDF

References


Kang Liu, LihengXu, and Jun Zhao, “Co-Extracting opinion Target and Opinion Words from Online Reviews Based on the Word Alignment Model”, VOL 27, NO. 3, MARCH 2015, pp. 636 - 650

M. Hu and B. Liu, “Mining opinion features in customer reviews,” in Proc. 19th Nat. Conf. Artif. Intell., San Jose, CA, USA, 2004, pp. 755 – 760

Kang Liu, Liheng Xu and Jun Zhao,“Syntactic Patterns versus Word Alignment: Extracting Opinion Targets from Online Reviews”, in 51st Annual Meeting of the Association for Computational Linguistics, Sofia, Bulgaria, August 4-9 2013, pp. 1754 – 1763

G. Qiu, L. Bing, J. Bu, and C. Chen, “Opinion word expansion and target extraction through double propagation,” Comput. Linguistics, vol. 37, no. 1, 2011, pp. 9 – 27

http://nlp.stanford.edu/software/lex-parser.shtml

A.-M. Popescu and O. Etzioni, “Extracting product features and opinions from reviews,” in Proc. Conf. Human Lang. Technol. Empirical Methods Natural Lang. Process., Vancouver, BC, Canada, 2005, pp. 339–346.

B. Wang and H. Wang, “Bootstrapping both product features and opinion words from chinese customer reviews with crossinducing,” in Proc. 3rd Int. Joint Conf. Natural Lang. Process., Hyderabad, India, 2008, pp. 289–295.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.



International Educational Scientific Research Journal is licensed under a Creative Commons Attribution 4.0 International License Based on a work at www.iesrj.com

Copyright © 2016 INTERNATIONAL EDUCATIONAL SCIENTIFIC RESEARCH JOURNAL.

Disclaimer: Articles on International Educational Scientific Research Journal have been previewed and authenticated by the Authors before sending for the publication. The Journal, Chief Editor and the editorial board are not entitled or liable to either justify or responsible for inaccurate and misleading data if any. It is the sole responsibility of the Author concerned.