Detecting Store Review Spammer via Review Relationship

Abstract:

Online review can help people getting more information about store or product. The potential customers tend to making decision according to it. However, driven by profit and fame, spammers post spurious reviews to mislead the customers by promoting or demoting target store. Previous studies mainly focused on the text features of the reviews. However, these studies ignore the importance of relationship between store and reviewer. This paper first proposes a novel concept of store robustness which means the degree that store resist the influence of spamming. Then which types of store the spammer prefer to choose to gain larger influence is discussed. The proposed method use store-reviewer relationship combined with deviation degree to calculate the spamicity (degree of spam) of reviews. A subset of highly suspicious reviewers is selected for evaluation by human judges. Experimental results show that the proposed method can find out the harmful store review spammer efficiently.

• Periodical: Advanced Materials Research (Volumes 718-720)
• Pages: 2153-2158
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.718-720.2153
• Online since: July 2013
• Authors: Qing Xi Peng, Jun Wei Chen
• Keywords: Review Relationship, Store Review Spammer, Store Robustness

References

[1] Jindal, N., Chang, B. Liu.: Review Spam Detection, WWW 2007, Banff, Alberta, Canada

[2] Jindal, N., Liu, B., Lim, E.P.: Finding Unusual Review Patterns using Unexpected Rules, CIKM (2010)

[3] Lim, E. P., Nguyen, V.A., Jindal, N., Liu, B., Lauw, H. W.: Finding Unusual Review Patterns using Unexpected Rules, CIKM (2010)

[4] Wang, G., Xie, S., Liu, B., Philip, S.Y.: Identify Online Store Review Spammers via Social Review Graph, ACM Transactions on Intelligent Systems and Technology, Volume 3 Issue 4, September 2012 Article No. 61

DOI: 10.1145/2337542.2337546

[5] Arjun Mukherjee, Bing Liu, Natalie Glance.: Spotting Fake Reviewer Groups in Consumer Reviews, WWW (2012)

[6] Rong Zhang, ChaoFeng Sha, Minqi Zhou, Aoying Zhou.: Exploiting shopping and reviewing behavior to re-score online evaluations, WWW (2012)

DOI: 10.1145/2187980.2188171

[7] Ravi Kant, Srinivasan H. Sengamedu, Krishnan S. Kumar.: Comment spam detection by sequence mining, WSDM (2012)

[8] Fangtao Li, Minlie Huang, Yi Yang, Xiaoyan Zhu.: Learning to identify review spam, IJCAI (2011)

[9] Myle Ott, Yejin Choi, Claire Cardie, Jeffrey T. Hancock.: Finding deceptive opinion spam by any stretch of the imagination, HLT (2011)

[10] Rong Zhang, ChaoFeng Sha, Minqi Zhou, Aoying Zhou.: Exploiting shopping and reviewing behavior to re-score online evaluations, WWW (2012)

DOI: 10.1145/2187980.2188171

[11] Guangyu Wu, Derek Greene, Barry Smyth, Pádraig Cunningham.: Distortion as a validation criterion in the identification of suspicious reviews, SOMA (2010)

DOI: 10.1145/1964858.1964860

[12] Fleiss, J.L., Cohen, J.: The equivalence of weighted kappa and the intraclass correlation coefficient as measures of reliability, Educational and psychological measurement

DOI: 10.1177/001316447303300309

[13] Edwin M. Knorr, Raymond T.NG.: A unified Notion of Outlier: Properties and Computation, KDD (1997)