垃圾邮件的概念漂移及过滤技术研究  

Research on concept drift and filtering for spam

作　　者：师文轩[1] 殷爱茹[1] 

机构地区：[1]南开大学软件学院,天津300071

出　　处：《中国科技论文》2014年第10期1111-1117,1130,共8页China Sciencepaper

基　　金：高等学校博士学科点专项科研基金资助项目(20130031120042);青年教师及海外留学归国人员研究启动项目(21220121035)

摘　　要：提出了双级别的概念漂移检测算法,监视已有的垃圾邮件过滤模型在对邮件分类时是否产生了持续的分类错误,进而对概念漂移进行识别。针对由用户偏好引起的垃圾邮件概念范畴变化,基于本体提出邮件数字指纹与概念子类别之间的关联强度和隶属度算法。通过对比实验,验证了所提方法在垃圾邮件概念漂移问题上的有效性。The dual-level concept drift detection algorithm was proposed to discern concept drift by monitoring sustained misclassi-fication of email classification.Regarding the spam concept scope changes caused by user preferences,the association and subjec-tion strength algorithm was proposed between email fingerprints and concept subcategories based ontology.In comparing experi-ments,the proposed method was proved effective to handle the concept drift problem in spam filtering.

关 键 词：机器学习 垃圾邮件过滤 概念漂移 数字指纹 

分 类 号：TP393.098[自动化与计算机技术—计算机应用技术]