您的位置:首页  > 论文页面

基于行为的新浪微博恶意用户识别

发表时间:2014-02-28  浏览量:2762  下载量:1165
全部作者: 林成峰,陈凯,周异,周曲
作者单位: 上海交通大学信息安全工程学院;上海交通大学电子信息与电气工程学院
摘 要: 以新浪微博为研究对象,提出一种基于行为特征检测微博恶意用户的方法。利用蜜罐账户、爬虫程序、淘宝购买等多种方法收集恶意用户样本。根据行为模式将恶意用户样本进行分类,得到3种恶意用户类型:过度广告、重复转发和过度关注。然后提取用户行为特征,通过数据统计分析以及与正常用户的比较,找出恶意用户的行为特点。最后,利用机器学习工具构造自动分类器用于自动鉴别恶意用户,并且在对分类器进行测试之后证实了该方法的可行性和准确性。
关 键 词: 计算机工程;新浪微博;恶意行为;恶意用户检测;机器学习
Title: Behavior-based identification of spammers in Sina weibo
Author: LIN Chengfeng, CHEN Kai, ZHOU Yi, ZHOU Qu
Organization: School of Information Security Engineering, Shanghai Jiao Tong University; School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University
Abstract: This paper proposed a method to identify spammers in Sina weibo based on their behavior features. We collected spammer samples using different methods such as using honeypot, using crawler and buying from online merchants. We divided spammers into three categories according to their behavior pattern: aggressive advertising, repeated duplicate reposting and aggressive following. We analyzed behavior and compared them with the legitimate users to extract features that could tell spammers from legitimate users. We built identification system with the help of machine learning toolkits. The evaluation result showed the effectiveness and accuracy of the identification system.
Key words: computer engineering; Sina weibo; spamming behavior; spammer detection; machine learning
发表期数: 2014年2月第4期
引用格式: 林成峰,陈凯,周异,等. 基于行为的新浪微博恶意用户识别[J]. 中国科技论文在线精品论文,2014,7(4):322-331.
 
0 评论数 0
暂无评论
友情链接