Email categorization using fast machine learning algorithms

초록

An approach to intelligent email categorization has been proposed using fast machine learning algorithms. The categorization is based on not only the body but also the header of an email message. The meta-data (e.g. sender name, organization, etc.) provide additional information that can be exploited and improve the categorization capability. Results of experiments on real email data demonstrate the feasibility of our approach. In particular, it is shown that categorization based only on the header information is comparable or superior to that based on all the information in a message.