| 基于HTML卡方算法的垃圾邮件过滤器设计 |
| |
| 引用本文： | 孔颖.基于HTML卡方算法的垃圾邮件过滤器设计[J].浙江科技学院学报,2010,22(6). |
| |
| 作者姓名： | 孔颖 |
| |
| 作者单位： | 浙江科技学院,信息与电子工程学院,杭州,310023 |
| |
| 摘 要： | 介绍基于HTML标签的卡方分布算法在垃圾邮件过滤中的应用。首先对通过浏览器收集到的邮件进行分析,将其转换为HTML源代码的形式,再根据HTML语言的特点对其进行特征提取,从而达到邮件预处理的目的。随后采用LVQ神经网络建立分类器模型,以达到最终分离正常邮件(ham)和垃圾邮件(spam)的目的。对比实验表明,结合HTML代码的卡方分布特征提取和LVQ神经网络的分类器模型效果更好。
|
| 关 键 词： | 垃圾邮件过滤 HTML标签 卡方分布 |
Design of spam filtering model based on HTML chi-square algorithm |
| |
| KONG Ying.Design of spam filtering model based on HTML chi-square algorithm[J].Journal of Zhejiang University of Science and Technology,2010,22(6). |
| |
| Authors: | KONG Ying |
| |
| Institution: | KONG Ying(School of Information and Electronic Engineering,Zhejiang University of Science and Technology,Hangzhou 310023,China) |
| |
| Abstract: | We introduce the application of chi-square distribution in spam filtering based on HTML tag algorithm.Firstly,we analyze the contents of the e-mail and convert them into forms of HTML source code.Then we do feature extraction according to HTML language characteristics so as to achieve the purpose of e-mail pre-processing.Finally,we use LVQ neural networks to design a classifier model in order to realize the purpose of separating ham from spam.The comparison test results show that the LVQ neural network clas... |
| |
| Keywords: | spam filtering HTML source tag chi-square |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
