Language-Independent Approaches to Detect Extremism and Collective Radicalisation Online

Due to lack of regulation, a lot of user-generated content reflects more closely the offline world than official news sources. Social media have become attractive platforms for anyone seeking independent information. Text mining and knowledge extraction are also crucial issues, in particular, directed toward social media and micro-blogging. The automatic identification of extremism and collective radicalisation require sophisticated Natural Language Processing (NLP) methods, text mining techniques, and resources, especially those dealing with opinions, emotions, or sentiment analysis. The area of understanding and detecting extremism and collective radicalism on social media has a connection with sentiment analysis and opinion mining. The main focus of this work is to provide the state-or-art to identify extremism and collective radicalisation on social networks based on user’s sentiment analysis, and to develop an unsupervised and language-independent approach by relying on statistical and probabilistic methods. This paper discusses few important case studies related to the roots of radicalism, extremism detection, and terrorism detection using sentiment analysis and present machine learning models, and how these methodologies can be exploited to develop our desire system. Keywords–Natural Language Processing; Social Media; Extremism; Collective Radicalisation; Sentiment Analysis