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.
