摘要
提出一种基于评论关系图的产品垃圾评论者检测方法.该方法考虑了评论者、评论、商店以及回复者之间的关系,构造出四者的评论关系图,根据评论真实度获得评论者的可信度,从而检测出产品垃圾评论者.实验结果表明,与未考虑可信回复者特征的识别方法相比,本文方法的准确率提升了4%.
We proposed a new method to spammer detection based on the review graph. The method captures the relationships among reviewers, reviews, stores and respondents, then we construct the review graph, and calculate the trustiness of reviewers according to honesty of reviews to identify suspicious reviewers. The experiment results show that the accuracy of this method has been improved by 4%, compared with the previous method without consideration of the respondents' trustiness.
出处
《福州大学学报(自然科学版)》
CAS
北大核心
2015年第2期170-175,共6页
Journal of Fuzhou University(Natural Science Edition)
基金
国家自然科学基金资助项目(61300105)
教育部博士点基金联合资助项目(2012351410010)
福建省高校产学合作科技重大项目(2010J05133)
福州市科技计划资助项目(2012-G-113
2013-PT-45)