Evaluating efficiency of classifier for email spam detector using hybrid feature selection approaches

As World Wide Web is expanding day by day, emails appear to be a reliable form of communication and the fastest way to send information from one place to another. Nowadays most of the transactions, be it general or business are taking place using emails as their mode of communication. Email is completely effective solution for communication as it helps in real time communication thereby saving time and expense. Apart from their advantages, emails are also affected by attacks that include spam mails. Spam mails are generally used to send bulk mails to a sender. Spam floods the Internet with many similar copies of messages that is distributed in depth; these messages are sent strongly to recipients who would not otherwise choose to receive it. We will analyze several methods of mining data for spam data in order to figure out the best classifier for sorting emails. As part of this paper, we explain the classification of emails to identify spam and not spam. For this purpose, we use the Naive Bayesian Classifier and created an email classification system to classify spam and not spam.