The Extremism Detection Using Hybrid Deep Learning

Abstract

Extremist groups often utilize social media to disseminate their ideas and beliefs in order to compile more new members and thereby help them spread violent content and extremist ideologies that threaten social cohesion. The goal of detecting extremism on social media is to identify and prevent the spread of these ideas through the use of artificial intelligence technologies that will help us detect extremist texts in social media. The dataset we used is called ISIS radical annotated tweets. In this study we used Deep learning techniques to classify extremism tweets, two different deep learning approaches were used (CNN-LSTM and LSTM). The CNN-LSTM combination produced the greatest results and had the highest accuracy (98.20%).