Detecting Extremism on Twitter During U.S. Capitol Riot Using Deep Learning Techniques

In the 21st century, social media platforms have become famous for communicating ideas, opinions, and emotions. These are influential in reaching out to youth, recruiting, spreading propaganda. Extremist groups now active users of platforms; therefore, it is necessary monitor their activities. Therefore, there an urgent need detect extremism on platforms. Existing research lacks a dedicated dataset provides minimal insights into texts. This study introduces development containing tweets collected from Twitter classifying texts as propaganda, recruitment, radicalization, non-extremism. The proposed evaluated using different Artificial Intelligence approaches such Bi-LSTM, BERT, RoBERTa, DistilBERT. Among four models, RoBERTa proved be most suitable detecting media, with accuracy 95%.