Research on Review Spam Detection Based on Sentiment Analysis in Electronic Commerce

Abstract:

With the wide adoption of the computer and network communication technology in our daily life, electronic business technology has seen a rapid development all over the world. It is common for electronic commerce websites to enable their customers to write reviews of products that they have purchased. Unfortunately, reviewers may write some untruthful opinions in order to promote or damage specific products reputation which called review spam. Product review spam detection makes an attempt to find untruthful opinions. In order to find the review spammers, the paper presents a review spam detecting based on sentiment analysis. Three feature behaviors of review spammers are recognized, including targeting at product type, targeting at product brand and targeting at product seller. The review spam detecting method based on sentiment analysis is suitable for detecting review spam, and is efficient and effective.

• Periodical: Applied Mechanics and Materials (Volumes 602-605)
• Pages: 2101-2104
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.602-605.2101
• Online since: August 2014
• Authors: Song Jie Gong*, Qiu Yuan Sheng
• Keywords: Product Review, Review Spam, Review Spam Detection, Sentiment Analysis

References

[1] Becchetti L, Castillo C, Donato D, et al. Link analysis for Web spare detection [J]. ACM Trans Web, 2008, 2 (1) : 1-42.

DOI: 10.1145/1326561.1326563

[2] Cortezp P, Correia A, Sousa P, et al. Spam email filtering using network-level properties I-C]/Proceedings of the 10th industrial conference on Advances in data mining: applications and theoretical aspects. Berlin, Germany. Springer-Verlag, 2010 : 476-489.

DOI: 10.1007/978-3-642-14400-4_37

[3] Rao D, Ravichandran D. Semi-supervised polarity lexicon induction [C]/Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics. Athens, Greece: Association for Computational Linguistics, 2009: 675-682.

DOI: 10.3115/1609067.1609142

[4] Stoyanov V, Cardie C. Topic identification for fine-grained opinion analysis [C]/Proceedings of the 22nd International Conference on Computational Linguistics-Volume 1. Manchester, United Kingdom: Association for Computational Linguistics, 2008. 817-824.

DOI: 10.3115/1599081.1599184

[5] Titov I, Mcdonald R. Modeling online reviews with multi-grain topic models [C]/Proeeeding of the 17th international conferenee on World Wide Web. Beijing, China: ACM, 2008: 111-120.

DOI: 10.1145/1367497.1367513

[6] Zhang Z, Varadaraj an B. Utility scoring of product reviews [ C ]/ Proceedings of the 15th ACM international conference on information and knowledge management. Arlington, Virginia, USA: ACM, 2006 : 51-57.

DOI: 10.1145/1183614.1183626

[7] Pang B, Lee L. Opinion Mining and Sentiment Analysis [J]. Found Trends InfRetr, 2008, 2(1/2): 1-135.