Title: Detecting spammers using review graph

Authors: Chonglin Gu; Zhixiang He; Shi Chen; Hejiao Huang; Xiaohua Jia

Addresses: Department of Computer Science and Technology, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen Key Laboratory of Internet Information Collaboration, Shenzhen 518055, China ' Department of Computer Science and Technology, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen Key Laboratory of Internet Information Collaboration, Shenzhen 518055, China ' Department of Computer Science and Technology, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen Key Laboratory of Internet Information Collaboration, Shenzhen 518055, China ' Department of Computer Science and Technology, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen Key Laboratory of Internet Information Collaboration, Shenzhen 518055, China ' Department of Computer Science and Technology, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen Key Laboratory of Internet Information Collaboration, Shenzhen 518055, China

Abstract: In recent years, e-commerce is so popular that many consumers make transactions online. In order to make more profit, some merchants hire spammers to give high ratings to promote certain products, or to give malicious negative reviews to defame products of competitors. Those misleading reviews are destructive to the fairness of e-commerce environment. Therefore, it is very important to detect spammers who are always posting deceptive reviews. However, existing methods have low recognition rate for detecting spam reviews. In this paper, we first propose to use SCTD to reduce the whole dataset, so that we can focus on the periods when spammers are more likely to happen. And then, a similarity graph is built to describe the relationships between those reviewers who post reviews on the same products. Finally, we propose an iterative algorithm to calculate the spam score for each reviewer using the edge weight and key features of adjacent reviewers in the graph. Experiment results show that our proposed method is much more effective in spammers detection.

Keywords: spammer detection; review spam; similarity graph.

DOI: 10.1504/IJHPCN.2017.086531

International Journal of High Performance Computing and Networking, 2017 Vol.10 No.4/5, pp.269 - 278

Received: 27 Sep 2015
Accepted: 14 Nov 2015
Published online: 12 Sep 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article