Detecting incentivized review groups with co-review graph

作     者：Yubao Zhang Shuai Hao Haining Wang 

作者机构：Department of Electrical and Computer EngineeringUniversity of DelawareNewarkDE 19716USA Department of Computer ScienceOld Dominion UniversityNorfolkVA 23529USA Bradley Department of Electrical and Computer EngineeringVirginia TechArlingtonVA 22203 USA 

出 版 物：《High-Confidence Computing》 (高置信计算(英文))

年 卷 期：2021年第1卷第1期

页      面：35-44页

核心收录：

学科分类：120202[管理学-企业管理（含：财务管理、市场营销、人力资源管理）] 12[管理学] 0202[经济学-应用经济学] 02[经济学] 1202[管理学-工商管理] 020205[经济学-产业经济学] 

主　　题：Incentivized review groups Co-review graph Community detection 

摘      要：Online reviews play a crucial role in the ecosystem of nowadays business(especially e-commerce platforms),and have become the primary source of consumer *** manipulate consumers’opinions,some sellers of e-commerce platforms outsource opinion spamming with incentives(e.g.,free products)in exchange for incen-tivized *** incentives,by nature,are likely to drive more biased reviews or even fake *** e-commerce platforms such as Amazon have taken initiatives to squash the incentivized review practice,sellers turn to various social networking platforms(e.g.,Facebook)to outsource the incentivized *** aggre-gation of sellers who request incentivized reviews and reviewers who seek incentives forms incentivized review *** this paper,we focus on the incentivized review groups in e-commerce *** perform the data collections from various social networking platforms,including Facebook,WeChat,and Douban.A measurement study of incentivized review groups is conducted with regards to group members,group activities,and *** identify the incentivized review groups,we propose a new detection approach based on co-review ***,we employ the community detection method to find the suspicious communities from co-review *** also build a“gold standarddataset from the data we collected,which contains the information of reviewers who belong to incentivized review *** utilize the“gold standarddataset to evaluate the effectiveness of our detection approach.