基于评论者关系的垃圾评论者识别研究  

Research on Review Spammer Detection via Reviewer Relationship

作　　者：徐小婷[1,2] 魏晶晶[3] 廖祥文[1,2] 刘月[1] 陈水利[4] 

机构地区：[1]福州大学数学与计算机科学学院,福建福州350108 [2]福建省网络计算与智能信息处理重点实验室,福建福州350108 [3]福建江夏学院,福建福州350108 [4]集美大学诚毅学院,福建厦门361021

出　　处：《集美大学学报（自然科学版）》2016年第2期146-152,共7页Journal of Jimei University：Natural Science

基　　金：国家自然科学基金青年项目(61300105);教育部博士点基金联合资助项目(2012351410010);福建省科技重大专项(2013H6012);福州市科技计划资助项目(2012-G-113;2013-PT-45)

摘　　要：垃圾评论者在很大程度上误导潜在消费者和观点挖掘系统。目前检测垃圾评论者的方法主要是基于评论、评论者和商店之间的关系,忽略了评论者之间的关系。针对上述问题,提出了基于评论者多边图的产品垃圾评论者检测方法。首先,以每个评论者为节点,评论者之间的关系为边,构建评论者之间的关系图模型;其次,根据多边图模型,提出了一种基于PageRank的评论者互评估可信度模型来检测垃圾评论者;最后,采用卓越亚马逊和Resellerrating.com平台上的数据进行验证。结果表明:该模型能够更有效地识别出垃圾评论者,在一定程度上解决了难识别仅发表一条评论的评论者的可信度问题。The review spammer greatly misleads the consumers and opinion mining system. Presently, the research of review spammer detection mainly is based on relationships among reviewers, reviews and stores, which doesn＇t take the relationships among reviewers into consideration. This paper proposes a multi- edge graph model to identify review spammer. Firstly, in the multi-edge graph model, the nodes represent reviewers and the edges represent the relationships among reviewers. Secondly, according to multi-edge graph model, reviewers＇ inter-assess trustiness model is based on PageRank algorithm to identify review spammer. And lastly, the datasets are crawled from JOYO Amazon website and Resellerrating. com. Experimental re- sults show that the model can achieve better performance on the accuracy of review spammer detection and the identification of review spammer who had only one review can be solved in some extent.

关 键 词：互评估 可信度 多边图模型 评论关系 垃圾评论者 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]