Email Spam Classification using Hybridized Technique with Feature Selection

Abstract: Email has becomes the major source of communication these days. Majority of people are using this mode of communication for their personal or professional use. Email is an effective, faster, secure and cheaper way of communication. The importance and usage for the email is growing day by day. It provides a way to easily transfer information globally with the help of internet. Because of extensive use of emails, spamming is growing day by day. According to the investigation, it is reported that a user receives more spam or irrelevant mails than ham or relevant mails. Spam is an unwanted, junk, unsolicited bulk message which is used to spreading virus, Trojans, malicious code, advertisement or to gain profit on negligible cost. Spam is a major problem that attacks the existence of electronic mails. So, it is very important to distinguish ham emails from spam emails, many methods have been proposed for classification of email as spam or ham emails. Spam filters are the programs which detect unwanted, unsolicited, junk emails such as spam emails, and prevent them to getting to the users inbox. Machine learning techniques, such as Na�ve Bayes, Support Vector Machine, Bagging and decision tree etc. In this paper we introduce a new Hybrid Technique with bagging to enhance the accuracy and performance of classification of emails into spam and ham.

Keywords: Ham, Spam, Email Spamming, Spam Filter, Email Spam.