A semi-automated hybrid approach to identify radicalization on social digital platform

Abstract

The digital social platform is an important medium for sharing or communicating a message from one person to another or one to many. The growth of internet users and social media use has also led to many adverse consequences. Such a platform is also used for radical activity by spreading the radical message in public. The detection of such a message is impossible by human monitoring. Many researchers are continually working on automatic detection of such activity to find a way to stop it. Automatic identification is also not possible due to the massive amount of data present and ambiguity in messages. The proposed work presents a framework for detecting the radical message and taking action by automatically blocking it. A dataset of 33k tweets has been fetched from twitter based on radical words. Two machine learning models, first countervectorizer and Logistic regression-based and second convolutional neural networks (CNN) have been applied yielding 96.97% accuracy. The provision of human intervention is also given in doubt cases which helps further to improve the accuracy of overall model. The framework gives very good results in a simulated environment.