A possibilistic framework for the detection of terrorism‐related Twitter communities in social media

Abstract

Summary Since the appearance of social networks, there was a historic increase of data. Unfortunately, terrorists are taking advantage of the easiness of accessing social networks and they have set up profiles to recruit, radicalize, and raise funds. Most of these profiles have pages that exist as well as new recruits to join the terrorist groups, see, and share information. Therefore, there is a potential need for detecting terrorist communities in social networks in order to search for key hints in posts that appear to promote the militants' cause. In order to remedy this problem, we first use a possibilistic‐clustering algorithm that allows more flexibility when assigning a social network profile to clusters (non‐terrorist, terrorist‐sympathizer, terrorist). Then, we introduce a new possibilistic flexible graph mining method to discover similar subgraphs by applying possibilistic similarity rather than using hard structural exact similarity. We experimentally show the efficiency of our possibilistic approach through a detailed process of tweets extract, semantic processing, and classification of the community detection.

Affective classification model based on emotional user experience and visual markers in YouTube video

“…At this stage, the most serious social, political, legal, and ethical issues relating to information technology will begin to surface on a large scale. Consistent with Moor's assertion, the use of the Internet by extremists to disseminate propaganda and engage in other illegal online activities has since surfaced [13,[23][24][25][26][27][28].…”

“…It contributes to the difficulty of policing activities that occur largely unregulated on the platform. Consider YouTube; despite community guidelines and administrative efforts, the platform maintains a massive archive of malicious and offensive videos [1,21,24,31,32]. Many of these videos remain online in the absence of a YouTube reviewer's flag request.…”

Multi-Ideology Multi-Class Extremism Classification Using Deep Learning Techniques

“…Thus, it is observed that deep learning techniques are better than machine learning algorithms in performance without using explicit feature extraction methods. The classification of extremism texts is either in binary [29][42] [43] or tertiary [35][47] [49] classes. These classes are 'extremist'-'non-extremist' [42], 'hate'-'non-hate' [50], etc.…”

Identifying the leaders and main conspirators of the attacks in terrorist networks

“…In addition to centrality-based measures, some researchers proposed learning-based methods [11,[39][40][41][42][43] in recent years to identify the key actors in terrorist networks. Johnston and Weiss [39] designed an approach that can automatically identify the related web pages and text content to Sunni extremist propaganda on social media, where a deep neural networkbased model is used to classify propaganda content from other social media content.…”