摘要
在线商品的销售与商品评价信息密切相关,拥有较多好评信息的商品更受消费者的青睐.于是越来越多的电商商家开始雇佣甚至充当虚假评论者对商品进行不切实际的评论,广大消费者成为了最终的受害者.本文提出一种基于评论者行为的虚假评论者检测方法,该方法从虚假评论者作弊动机出发,综合考虑评论者评价行为、评论者交流行为以及评论者对商品的关注行为,将评论者行为视为证据并构建D-S证据理论模型.首先,本文利用多种维度对评论者的三种行为特征进行量化并构建三个独立的SVM模型,然后将SVM无阈值输出通过sigmoid函数实现后验概率输出,最后将其用于证据融合并根据识别框架下的证据支持度对评论者身份进行检测.实验结果表明,本文提出的方法准确有效.
Online product reviews can significantly affect quantity of sale,and consumers are more willing to buy products with high ratings and positive comments. Therefore,more and more online sellers began to hire or act as review spammers to write untruthful product reviews. There is no doubt that all of the consumers suffered from these fake reviews in the end. This paper proposes a method for review spammer detection based on reviewer′s behaviors. We notice review spammer′s cheating motivation and take reviewer′s review behavior,communicative behavior and their behavior of targeting specific commodities into consideration. Regarding these three behaviors as evidence,we propose a model based on the D-S evidence theory. Firstly,we define several dimensionalities to quantify reviewer′s three types of behaviors and construct three different SVM models to reflect these behaviors. Secondly,we get posterior probability by inputting the unthresholded output of an SVM into the sigmoid function. Then we create basic probability assignment by means of posterior probability and use the Dempster rules of evidence combination. Finally,we can detect review spammer on the basis of combined basic probability assignment. Experimental results show that our method is effective and accurate in detecting review spammers.
作者
张文宇
岳昆
张彬彬
ZHANG Wen-yu;YUE Kun;ZHANG Bin-bin(School of Information Science and Engineering,Yunnan University,Kunming 650500,China)
出处
《小型微型计算机系统》
CSCD
北大核心
2018年第11期2428-2435,共8页
Journal of Chinese Computer Systems
基金
国家自然科学基金项目(61472345
61402398)资助
第二批"云岭学者"培养项目(C6153001)资助
云南省应用基础研究计划重点项目(2014FA023)资助
云南大学青年英才培育计划(WX173602)资助
云南省教育厅科(2017ZZX228)资助
