Dynamic Matrix of Extremisms and Terrorism (DMET): A Continuum Approach Towards Identifying Different Degrees of Extremisms

• URL: http://arxiv.org/abs/2312.00337v1
• Date: Fri, 1 Dec 2023 04:13:48 GMT
• Title: Dynamic Matrix of Extremisms and Terrorism (DMET): A Continuum Approach Towards Identifying Different Degrees of Extremisms
• Authors: Marten Risius, Kevin M. Blasiak, Susilo Wibisono, Rita Jabri-Markwell, Winnifred Louis
• Abstract summary: We propose to extend the current binary understanding of terrorism (versus non-terrorism) with a Dynamic Matrix of Extremisms and Terrorism (DMET) DMET considers the whole ecosystem of content and actors that can contribute to a continuum of extremism. It organizes levels of extremisms by varying degrees of ideological engagement and the presence of violence.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We propose to extend the current binary understanding of terrorism (versus non-terrorism) with a Dynamic Matrix of Extremisms and Terrorism (DMET). DMET considers the whole ecosystem of content and actors that can contribute to a continuum of extremism (e.g., right-wing, left-wing, religious, separatist, single-issue). It organizes levels of extremisms by varying degrees of ideological engagement and the presence of violence identified (e.g., partisan, fringe, violent extremism, terrorism) based on cognitive and behavioral cues and group dynamics. DMET is globally applicable due to its comprehensive conceptualization of the levels of extremisms. It is also dynamic, enabling iterative mapping with the region- and time-specific classifications of extremist actors. Once global actors recognize DMET types and their distinct characteristics, they can comprehensively analyze the profiles of extremist actors (e.g., individuals, groups, movements), track these respective actors and their activities (e.g., social media content) over time, and launch targeted counter activities (e.g. de-platforming, content moderation, or redirects to targeted CVE narratives).

Related papers

• Unifying the Extremes: Developing a Unified Model for Detecting and Predicting Extremist Traits and Radicalization [13.611821646402818]
  We propose a novel method for extracting and analyzing extremist discourse across a range of online community forums. By focusing on verbal behavioral signatures of extremist traits, we develop a framework for quantifying extremism at both user and community levels. Our findings contribute to the study of extremism by introducing a more holistic, cross-ideological approach.
  arXiv  Detail & Related papers  (2025-01-08T20:17:24Z)
• Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective [69.25513235556635]
  Adversarial machine learning (AML) studies the adversarial phenomenon of machine learning, which may make inconsistent or unexpected predictions with humans. Some paradigms have been recently developed to explore this adversarial phenomenon occurring at different stages of a machine learning system. We propose a unified mathematical framework to covering existing attack paradigms.
  arXiv  Detail & Related papers  (2023-02-19T02:12:21Z)
• Countering Malicious Content Moderation Evasion in Online Social Networks: Simulation and Detection of Word Camouflage [64.78260098263489]
  Twisting and camouflaging keywords are among the most used techniques to evade platform content moderation systems. This article contributes significantly to countering malicious information by developing multilingual tools to simulate and detect new methods of evasion of content.
  arXiv  Detail & Related papers  (2022-12-27T16:08:49Z)
• Physical Adversarial Attack meets Computer Vision: A Decade Survey [55.38113802311365]
  This paper presents a comprehensive overview of physical adversarial attacks. We take the first step to systematically evaluate the performance of physical adversarial attacks. Our proposed evaluation metric, hiPAA, comprises six perspectives.
  arXiv  Detail & Related papers  (2022-09-30T01:59:53Z)
• DISARM: Detecting the Victims Targeted by Harmful Memes [49.12165815990115]
  DISARM is a framework that uses named entity recognition and person identification to detect harmful memes. We show that DISARM significantly outperforms ten unimodal and multimodal systems. It can reduce the relative error rate for harmful target identification by up to 9 points absolute over several strong multimodal rivals.
  arXiv  Detail & Related papers  (2022-05-11T19:14:26Z)
• From Motor Control to Team Play in Simulated Humanoid Football [56.86144022071756]
  We train teams of physically simulated humanoid avatars to play football in a realistic virtual environment. In a sequence of stages, players first learn to control a fully articulated body to perform realistic, human-like movements. They then acquire mid-level football skills such as dribbling and shooting. Finally, they develop awareness of others and play as a team, bridging the gap between low-level motor control at a timescale of milliseconds.
  arXiv  Detail & Related papers  (2021-05-25T20:17:10Z)
• Learning future terrorist targets through temporal meta-graphs [8.813290741555994]
  We propose the use of temporal meta-graphs and deep learning to forecast future terrorist targets. We derive 2-day-based time series that measure the centrality of each feature within each dimension over time. Formulating the problem in the context of the strategic behavior of terrorist actors, these multivariate temporal sequences are then utilized to learn what target types are at the highest risk of being chosen.
  arXiv  Detail & Related papers  (2021-04-21T08:09:57Z)
• #ISIS vs #ActionCountersTerrorism: A Computational Analysis of Extremist and Counter-extremist Twitter Narratives [2.685668802278155]
  This study will apply computational techniques to analyse the narratives of various pro-extremist and counter-extremist Twitter accounts. Our findings show that pro-extremist accounts often use different strategies to disseminate content when compared to counter-extremist accounts across different types of organisations.
  arXiv  Detail & Related papers  (2020-08-26T20:46:45Z)
• A Bayesian decision support system for counteracting activities of terrorist groups [0.0]
  Terrorist groups present a serious threat to the security and well-being of the general public. Such observable behaviour and communications data can be utilised by the authorities to estimate the threat posed by a terrorist group. Here we develop a Bayesian integrating decision support system that can bring together information relating to each of the members of a terrorist group as well as the combined activities of the group.
  arXiv  Detail & Related papers  (2020-07-08T20:23:25Z)
• FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding [118.32912239230272]
  FineGym is a new action recognition dataset built on top of gymnastic videos. It provides temporal annotations at both action and sub-action levels with a three-level semantic hierarchy. This new level of granularity presents significant challenges for action recognition.
  arXiv  Detail & Related papers  (2020-04-14T17:55:21Z)
• A Complex Networks Approach to Find Latent Clusters of Terrorist Groups [5.746505534720595]
  We build a multi-partite network that includes terrorist groups and related information on tactics, weapons, targets, active regions. We show that groups belonging to opposite ideologies can share very common behaviors and that Islamist/jihadist groups hold behavioral characteristics with respect to the others.
  arXiv  Detail & Related papers  (2020-01-10T10:08:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.