A Probabilistic Machine Learning Approach for Identifying Text Spams

With increased internet usage, one of the most prevalent problems faced is constant spamming. While web applications and mailing services are heavily spammed, the upsurge of handheld mobile devices has led to an outburst of heavy mobile spamming. The matter is more severe in mobile devices due to lesser sophisticated filtering mechanisms in built in mobile operating systems. Spam detection is challenging due to the need for semantic analysis of the mobile spam messages, which generally tend to have overlapping polarities. In this work, a mobile spam classification technique is developed based on Adaptive Neuro Fuzzy Inference System (ANFIS) comprising of Gini’s index Fuzzy and Back-propagation in machine learning. The approach uses the Gini’s splitting criteria for the data sets and backpropagation based neural network as the machine learning classifier. The evaluation of the proposed system is based on the accuracy of classification and number of iterations. The results obtained in the proposed work are compared with existing techniques and it is shown that the proposed technique outperforms them in terms of accuracy of classification.