融合情感极性与信任函数的虚假评论检测方法  

A fake review detection method using emotional and belief function

作　　者：杨丰瑞[1,2,3] 吴晓浩 万程峰 YANG Feng-rui;WU Xiao-hao;WAN Cheng-feng(School of Communication and Information Engineering,Chongqing University of Posts and Telecommunications,Chongqing 400065;Research Center of New Telecommunication Technology Applications,Chongqing University of Posts and Telecommunications,Chongqing 400065;Chongqing Chongyou Information Technology (Group)Co.Ltd.,Chongqing 401121,China)

机构地区：[1]重庆邮电大学通信与信息工程学院,重庆400065 [2]重庆邮电大学通信新技术应用研究中心,重庆400065 [3]重庆重邮信科(集团)股份有限公司,重庆401121

出　　处：《计算机工程与科学》2019年第9期1679-1685,共7页Computer Engineering & Science

摘　　要：在线评论是用户判断商品质量的一个依据。虚假评论严重影响了消费者的购买行为,现有的虚假评论检测方法从文本出发,忽略了评分的虚假性,评分通常是不精确和不确定的,对虚假评论检测效果不佳。提出融合情感极性与信任函数的虚假评论检测方法(EP-BFRD),利用信任函数处理给定评论者评分中的不确定性和不准确性,考虑与其他评分者提供的评分的相似性,以检测误导性,并判断评论文本情感极性与评分一致性。综合考虑信任函数处理的结果以及评分与文本情感一致性的结果来判断评论的虚假性。在一个真实的数据库上进行实验,实验表明该方法可有效解决虚假评论检测问题。Online comments are a basis for users to judge the quality of a product, and fake reviews seriously affect the purchase behavior of consumers. Existing fake review detection methods focus on the text and ignore the falseness of scores. Due to inaccurate and uncertain scoring, fake review detection does not work well. We propose a fake review detection method(EP-BFRD) using emotional polarity and trust function. The trust function is used to deal with the uncertainty and inaccuracy in a given reviewer’s score, which are then combined with the similarity to other provided ratings to detect misleading, and to judge the consistency between the emotional polarity of the review text and the score. A fake review is determined by both the processing results of the trust function and the consistency between the scores and text emotion. Experiments on a real database show that the proposed method is an effective solution to fake review detection problem.

关 键 词：虚假评论 情感极性 信任函数 虚假评论检测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]