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

Abstract

Terrorist organizations use different social media as a

tool for spreading their views and influence general people to join

their terrorist activities. Twitter is the most common and easy way to

reach mass people within a small amount of time. In this paper, 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 frontend for real-time viewing of the

tweets that are detected using this system. We have also compared

the performance of two different machine learning classifiers,

Support Vector Machine (SVM) and Multinomial Logistic

Regression and found the first one works better. As our system is

highly dependent on 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 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 their views or spread fear among

general people.