基于人工免疫危险理论的微博水军用户检测研究  

Study on Detection of Weibo Spammers Based on Danger Theory in Artificial Immunity System

作　　者：杨超 秦廷栋 范波 李涛[3] YANG Chao;QIN Ting-dong;FAN Bo;LI Tao(School of Computer Science and Information Engineering,Hubei University,Wuhan 430062,China;Office of Scientific Research and Development,Wuhan University,Wuhan 430072,China;Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System,Wuhan University of Science and Technology,Wuhan 430065,China)

机构地区：[1]湖北大学计算机与信息工程学院,武汉430062 [2]武汉大学科学技术发展研究院,武汉430072 [3]智能信息处理与实时工业系统湖北省重点实验室(武汉科技大学),武汉430065

出　　处：《计算机科学》2018年第11期138-142,159,共6页Computer Science

基　　金：武汉科技大学智能信息处理与实时工业系统湖北省重点实验室基金(znxx2018MS05)资助

摘　　要：将人工免疫危险理论引入到用户行为特征的分析中,以有效地识别微博水军用户。以新浪微博为例,分析了新浪微博水军的行为特征,选取微博总数、微博等级、是否认证、阳光信用、粉丝数等特征属性,将属性分析结果作为区别水军与正常用户的特征信号,并基于树突状细胞算法(Dendritic Cells Algorithm,DCA)实现新浪微博水军的识别。使用新浪微博用户的真实数据对算法的有效性进行了验证和对比实验,结果表明该方法能够有效检测出新浪微博中的水军用户,具有较高的检测准确率。This paper introduced the danger theory in artificial immunity system into the analysis of user behavior cha-racteristics to identify the spammers in Weibo effectively.Taking Sina Weibo as an example,this paper analyzed the behavior characteristics of Weibo spammers,selected the total number of Weibo,Weibo level,user authentication,sunshine credit and the number of fans as attribute characteristics and used the analysis results of attribute characteristics as the characteristic signals of distinguishing the spammers and the normal users.After that,the recognition of Sina Weibo spammers can be achieved based on Dendritic Cells Algorithm.The real data of Sina Weibo users was used to verify the effectiveness of the proposed algorithm and conducted comparison experiments.The experimental results suggest that this algorithm can effectively detect the spammers in Sina Weibo and has high detection accuracy.

关 键 词：微博水军 行为特征 人工免疫 危险理论 树突状细胞算法 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]