基于Nave Bayes模型的垃圾邮件过滤方法  

A Spam Filtering Method Based on Nave Bayes Model

作　　者：魏晓宁[1] 朱巧明[1] 

机构地区：[1]苏州大学

出　　处：《南通大学学报（自然科学版）》2008年第1期54-57,共4页Journal of Nantong University(Natural Science Edition)　

摘　　要：采用信息增益进行特征选择,以改进的朴素贝叶斯分类算法进行邮件分类.利用文本特征估算文本属于两种类型的偏测度,以此构造二维文本空间.将文本映射为二维空间中的一个点,将分类算法看作是在二维空间中寻求一条分割直线,根据文本点到分割直线的距离来判断该邮件为何类邮件.In spare filtering, the way of information gain is adopted to undertake feature selection and the improved Na？ve Bayes classification algorithm is used to classify the mails. Meanwhile, a two-dimensional text Space is configurated in terms of either bias degree of a text. Mapping the text to a point in the two-dimensional space, and considering the classification algorithm the search for a cutting straight line in the two-dimensional space, we can classify the mails according to the distance between the point and the cutting straight line.

关 键 词：垃圾邮件过滤 信息增益 特征选择 朴素贝叶斯 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]