Automated Spam Filtering through Data Mining Approach

Abstract

Spam messages can be referred as those mails which come into act in the absence of a standard agreement among the senders and receivers for receiving e-mail solicitation. Usually these messages are sent in bulk quantities. For preventing the spam delivery, an automatic system based spam filter tool is employed. The objectives of spam filters and spam are contradicted diametrically. A spam filter can be termed effective if it recognizes spam. On the other hand, it is ineffective when it escapes the filters. It is the need of the hour that these bulk unsolicited e-mails be effectively filtered. Increasing volume of these mails emphasizes on the requirement and design of dependable anti-spam filters. One of the techniques which is used widely to filter these spam e-mails is the machine learning technique. They possess in built algorithms which filters spam e-mails at commendable rates. In this project we present a method, to access classifier security against their attacks profoundly concentrating on the content of the message. The dependence on a predefined set of keywords is reduced. The paper also focuses on related works which apply machine learning techniques using naïve Bayes classification for e-mail message classification.