JOURNAL OF COMPUTERS (JCP)
ISSN : 1796-203X
Volume : 4    Issue : 3    Date : March 2009

Research on E-mail Filtering Based On Improved Bayesian
Pei-yu Liu, Li-wei Zhang, and Zhen-fang Zhu
Page(s): 271-275
Full Text:
PDF (120 KB)


Abstract
Naive Bayesian has been widely used in spam filter because it simply and it also could classify
texts more correctly and quickly. However, in the process of classifying and filtering, the traditional
method doesn't consider the different features between the spam mail and the legitimate mail, and
it also doesn't take into account the loss of misclassifying legitimate mail as spam, so there are
many limitations of e-mail filtering. An improved algorithm based on Naïve Bayesian and Boosting
method is proposed in this paper. The experiment result shows that the improved algorithm has
better performance.

Index Terms
Spam; E-mail Filtering; Bayesian Algorithm; Boosting method