Method of Spam Filtering Based on Term Expansion
Gao Liang · Journal of Zhongyuan University of Technology · 2009
This article proposes a new method of expanding the sensitive terms based on statistics.By the use of sensitive terms which are collected manully,the weight of other terms in spam will be calculated.The higher weighted terms will be selected as secondary sensitive terms and be classfied.As a supplementary,the secondary sensitive terms will help to filter the spam.This method is not only suitable for Chinese,but also for English text.The experiment indicated that this method can improve the recalling rate and the precision of spam filtration.