| 一种基于动态特征词典的SVM中文电子邮件过滤方法 |
| |
| 引用本文： | 侯岩,王文剑.一种基于动态特征词典的SVM中文电子邮件过滤方法[J].计算机科学,2008,35(3):49-51. |
| |
| 作者姓名： | 侯岩 王文剑 |
| |
| 作者单位： | 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 |
| |
| 基金项目： | 国家自然科学基金
,
山西省高等学校科研开发基金
,
山西省留学人员科技活动择优资助项目
,
山西省高等学校青年学术带头人项目 |
| |
| 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(Suppo~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.
|
| 关 键 词： | 支持向量机 中文电子邮件 过滤 动态特征词典 |
A SVM Chinese E-mail Filtering Approach Based on Dynamic Feature Dictionary |
| |
| HOU Yan,WANG Wen-Jian.A SVM Chinese E-mail Filtering Approach Based on Dynamic Feature Dictionary[J].Computer Science,2008,35(3):49-51. |
| |
| Authors: | HOU Yan WANG Wen-Jian |
| |
| Affiliation: | HOU Yan WANG Wen-Jian(School of Computer & Information Technology,Key Laboratory of Computational Intelligence & Chinese Information Processing of Ministry of Education,Shanxi University,Taiyuan 030006) |
| |
| Abstract: | 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 ... |
| |
| Keywords: | Support vector machine Chinese E-mail Filter Dynamic feature dictionary |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
点击此处可从《计算机科学》下载全文 |
|
