Abstract

Spam email has already caused many problems such as taking recipient time and wasting network bandwidth. It is time consuming and laborious to remove spam email by hand if there are too many spam email in mailbox. Thus, automatic classification of spam email from legitimate email has become very important. Decision tree and ensemble learning are two popular and powerful techniques in machine learning community. In this study, a novel classification method based decision tree and ensemble learning is introduced to classify the spam email effectively. An experimental evaluation of different methods is carried out on a public spam email dataset. The experimental results suggest that the proposed method generally outperforms benchmark techniques.

Paper Details