基于改进蚁群算法的集体垃圾邮件发送者检测研究  

Research on Collective Spammers Detection Based on Improved Ant Colony Algorithm

作　　者：宁梦霞 陈虎杰 Mengxia Ning;Hujie Chen(Business School,University of Shanghai for Science and Technology,Shanghai)

机构地区：[1]上海理工大学管理学院,上海

出　　处：《运筹与模糊学》2024年第5期549-560,共12页Operations Research and Fuzziology

摘　　要：社交媒体评论对购物至关重要,但不良商家组织欺诈性评价者发布恶意评论,误导消费者。本文提出了一种名为IACOA的改进蚁群算法,通过评论投影图检测隐式社区,提高垃圾邮件发送者的识别精度。该算法在审查者投影图中执行,使用组和个人垃圾邮件指标评估意见垃圾邮件发送者组的怀疑度,并输出排名。该方法在预测精度上优于其他四种比较方法。Social media reviews are crucial for shopping,but unscrupulous merchants organize fraudulent reviewers to post malicious reviews and mislead consumers.In this paper,we propose an improved ant colony algorithm called IACOA to improve the spammer identification accuracy by detecting implicit communities through review projection maps.The algorithm executes in the reviewer projection map,evaluates the skepticism of the opinion spammer group using group and individual spam metrics,and outputs the rankings.The method outperforms the other four comparative methods in terms of prediction accuracy.

关 键 词：社交媒体评论 改进蚁群算法 垃圾邮件发送者 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]