Impact of Feature Selection Technique on Email Classification

Being one of the most powerful and fastest way of communication, the popularity of email has led to untoward rise of email spam. Spam are unwanted and unsolicited messages and the subsequent rise of spam received by email users has become a serious security threat. Automatic filtering of spam emails, hence, is a promising and research worthy area whereupon extensive work has been reported about attempts to design machine learning based classifiers. Herein feature selection technique can be conveniently applied for developing efficient machine learning based classifiers. However, feature selection techniques provide a mechanism to identify suitable and relevant features (attributes) for any knowledge discovery task. The choice of selecting a suitable feature selection technique is always a key question of research. The present paper compares and discusses the effectiveness of two feature selection methods i.e. Chi-square and Info-gain on machine learning techniques namely Bayes algorithm, tree-based algorithm and support vector machine with a purpose to design a classifier for spam email filtering. The experiment is performed using 10-fold cross-validation and performance measures such as accuracy, precision, recall are used to compare the results.