一种基于动态特征词典的SVM中文电子邮件过滤方法  

A SVM Chinese E-mail Filtering Approach Based on Dynamic Feature Dictionary

作　　者：侯岩[1] 王文剑[1] 

机构地区：[1]山西大学计算机与信息技术学院计算智能与中文信息处理教育部重点实验室,太原030006

出　　处：《计算机科学》2008年第3期49-51,共3页Computer Science

基　　金：国家自然科学基金(60673095);山西省高校科技研究开发项目(200611001);山西省留学人员科技活动择优资助项目;山西省高校青年学术带头人基金资助

摘　　要：随着电子邮件的广泛应用,泛滥成灾的垃圾邮件对人们的生活和网络安全带来了严重的威胁,反垃圾邮件问题已成为全球性的具有现实意义的问题。本文提出了一种基于动态特征词典的SVM中文邮件过滤方法,通过动态构造特征词典以及选择合适的支持向量机(Support Vector Machine,SVM)核参数,有效地提高了垃圾邮件的过滤精度,实验结果超过了网易免费邮所公布的过滤指标。With the widely use of email, amounts of spams are fiercely threatening the safety of the internet and the lives of people. Anti-spam problem has become an international, significant and practical topic now. This paper presents a SVM Chinese email filtering approach based on dynamic feature dictionary. By constructing a dynamic feature dictionary and selecting the parameter of SVM kernel, the presented approach can improve the correct rejection rate of filtering spams dramatically. The simulation results show that the filtering factors of the presented approach can beyond those published by NetEase Free E-mail.

关 键 词：支持向量机 中文电子邮件 过滤 动态特征词典 

分 类 号：TP393.098[自动化与计算机技术—计算机应用技术] TP311.52[自动化与计算机技术—计算机科学与技术]