A technique to differentiate spam short message service (sms) from mobile data /

Abstract

Today text messages have a signi cant impact on our lives, but at the same time we face many critical problems due to SMS spamming. Therefore to detect spam messages and distinguish it via accurate ltering is a challenging task for researchers. In current research work content based spam SMS ltering technique is proposed depending on machine learning approach to distinguish spam messages from mobile data while considering the low processing power and limited memory of mobile phones. From each text message; ve attributes are extracted and based on these attributes/features, an unknown/unlabelled SMS message can be classi ed as spam or ham by a trained learning algorithm. These attributes are the length of the text message and presence of repeatedly occurring spam words, count of spam words, combination of spam words and SMS class. It is shown that Decision Tree classi er performance is better than other machine learning algorithms investigated. The other learning algorithms explored in this work are Nave Bayes and neural network architecture-Multilayer Perceptron Algorithm.