A Framework for Analyzing Real-Time Tweets to Detect Terrorist Activities

Abstract

Terrorist organizations use different social media as a kind of tool for spreading their views and influence general people to join their terrorist activities. Twitter is one of the the most common and easy way to reach mass people within short time span. We have focused on the development of a system that can automatically detect terrorism-supporting tweets by real-time analyzation. In this system, we have developed a front-end system for real-time viewing of the tweets from twitter that are detected using this system. We also have compared the performance of the two different machine learning classifiers, Support Vector Machine (SVM) and Multinomial Logistic Regression and found that the first one works better than the second one. As our system is highly dependent on the data, for more accuracy we added a re-train module. By using this module wrongly classified tweets can be added to the training dataset and can train the whole system again for better performance. This system will help to ban the terrorist accounts from twitter so that they can’t promote terrorism, their views or spread fear among general people in society.