垃圾商品评论检测研究综述

计算机工程与科学

垃圾商品评论检测研究综述

张圣,伍星,邹东升

（重庆大学计算机学院,重庆 400044）

收稿日期:2017-06-29 修回日期:2017-11-09 出版日期:2018-11-25 发布日期:2018-11-25
基金资助:
国家自然科学基金(61309013);重庆市科技计划项目基础科学与前沿技术研究专项项目(Cstc2014jcyjA40042)

Review:Detection of product review spam

ZHANG Sheng,WU Xing,ZOU Dongsheng

（College of Computer Science,Chongqing University,Chongqing 400044,China）

Received:2017-06-29 Revised:2017-11-09 Online:2018-11-25 Published:2018-11-25

摘要/Abstract

摘要：

商品评论对消费者的购买意愿有明显导向作用，欺诈者可杜撰评论来过度褒奖或恶意贬低商品,以此来促进己方或是打击对方的商品销售，垃圾商品评论检测成为了一项迫切需要的技术。首先将相关研究分为以评论内部（文本特征）为中心和以评论外部（文本特征）为中心的两大类,然后分别综述它们在特征选择、学习方法上的研究进展,并介绍了垃圾商品评论检测领域的常用评论数据集,在此基础上,展望了该领域的热点研究方向。

关键词: 垃圾商品评论, 文本特征, 行为特征, 评论数据集

Abstract:

E-commerce website's product reviews have a guiding effect on the user's purchase intention. However, spammers may create fake reviews to artificially promote or demote target products. Techniques for detecting review spam therefore have become an urgent need. We first divide the related researches into two categories: internal review (text features) -centric and external reviews (behavior features) -centric. Then, their research progresses on feature selection and machine learning methods are summarized. The common data sets in product review spam detection are summarized. Finally, we point out some potential research directions based on the review.

Key words: product review spam, text feature, behavior feature, opinion data set

张圣,伍星,邹东升. 垃圾商品评论检测研究综述[J]. 计算机工程与科学.

ZHANG Sheng,WU Xing,ZOU Dongsheng. Review:Detection of product review spam[J]. Computer Engineering & Science.