Email Classification Using Back Propagation Technique

This paper proposes a new email classification model using a teaching process of multi-layer neural network to implement back propagation technique. Email has become one of the fastest and most efficient forms of communication. However, the increase of email users with high volume of email messages could lead to un-structured mail boxes, email congestion, email overload, unprioritised email messages, and resulted in the dramatic increase of email classification management tools during the past few years. Our contributions are: the use of empirical analysis to select an optimum, novel collection of features of a users’ email contents that enable the rapid detection of most important words, phrases in emails and a demonstration of the effectiveness of two equal sets of emails training and testing data.