An Initial Study on Radicalization Risk Factors: Towards an Assessment Software Tool

Radicalization has increasingly become a transnational risk as cyber-technologies and social networks have steadily improved in the past years. DAESH has utilized the benefits of these new technologies to radicalize and recruit home-grown fighters, inviting them to join their ranks in the Islamic State territories, or inciting them to attack in their Western countries. However, this process of radicalization is not a simple task. Jihadist recruiters take advantage of certain vulnerable individuals who are better targets for radicalization. Academics have subsequently attempted to identify and examine these characteristics, which can be useful in identifying people who may be vulnerable to jihadist rhetoric. Violence risk assessment is a method which has been used by psychologists, Law Enforcement Agencies, prosecutors and other relevant actors, in order to assess the risk of an individual to commit violent acts. As terrorist or political violence is not comparable with other types of violence, specialized tools are needed to calculate the risk of radicalization or attack threat. This paper tries to gather the risk factors associated with violent extremism and jihadist radicalization from the literature and the risk assessment tools already available or under development. This paper presents some details related to the RiskTrack software tool, which is currently under development by behavioral researchers and computer engineers. The RiskTrack software tool aims to automatically assess an individual's risk of becoming radicalized. This is done by analyzing social media profiles and testing for specific factors that have been found to be associated with radicalization.

[1]  Arie W. Kruglanski,et al.  Terrorism, radicalization, and de-radicalization , 2016 .

[2]  M. Crenshaw.  The Causes of Terrorism , 1981 .

[3]  Jason J. Jung,et al.  ACO-based clustering for Ego Network analysis , 2017, Future Gener. Comput. Syst..

[4]  Home grown terrorism and Islamist radicalisation in Europe , 2007 .

[5]  J. Horgan,et al.  From Profiles to Pathways and Roots to Routes: Perspectives from Psychology on Radicalization into Terrorism , 2008 .

[6]  Elizabeth Pearson.  The Case of Roshonara Choudhry: Implications for Theory on Online Radicalization, ISIS Women, and the Gendered Jihad , 2016 .

[7]  Shintaro Okazaki,et al.  Combining social-based data mining techniques to extract collective trends from twitter , 2014 .

[8]  David Camacho,et al.  Adaptive k-Means Algorithm for Overlapped Graph Clustering , 2012, Int. J. Neural Syst..

[9]  Gabriel Ong,et al.  Combating Violent Extremism and Radicalization in the Digital Era , 2016 .

[10]  David Camacho,et al.  Using the Clustering Coefficient to Guide a Genetic-Based Communities Finding Algorithm , 2011, IDEAL.

[11]  Antonio González-Pardo,et al.  Behaviour-based identification of student communities in virtual worlds , 2014, Comput. Sci. Inf. Syst..

[12]  John Monahan,et al.  The Individual Risk Assessment of Terrorism , 2011 .

[13]  A. Silke.  Holy Warriors , 2008 .

[14]  Mitchell D. Silber,et al.  Radicalization in the West: The Homegrown Threat , 2007 .

[15]  David Camacho,et al.  Evolutionary clustering algorithm for community detection using graph-based information , 2014, 2014 IEEE Congress on Evolutionary Computation (CEC).

[16]  Regina Blaskie.  Women in the Religious Wave of Terrorism and Beyond: The West Versus the Rest An analysis of women’s motives and agency in Al-Qaeda and the Islamic State , 2016 .

[17]  Kamaldeep Bhui,et al.  Is Violent Radicalisation Associated with Poverty, Migration, Poor Self-Reported Health and Common Mental Disorders? , 2014, PloS one.

[18]  Robyn Torok.  “Make A Bomb In Your Mums Kitchen”: Cyber Recruiting And Socialisation of ‘White Moors’ and Home Grown Jihadists , 2010 .

[19]  D. Pressman,et al.  Internet Use and Violent Extremism: A Cyber-VERA Risk Assessment Protocol , 2016 .

[20]  Fernando E. B. Otero,et al.  Medoid-based clustering using ant colony optimization , 2016, Swarm Intelligence.

[21]  Djamal Benslimane,et al.  Measuring the Radicalisation Risk in Social Networks , 2017, IEEE Access.

[22]  Elena Mastors,et al.  Omar al-Hammami: a case study in radicalization. , 2014, Behavioral sciences & the law.

[23]  R. Borum.  Psychological vulnerabilities and propensities for involvement in violent extremism. , 2014, Behavioral sciences & the law.

[24]  M. Lloyd,et al.  Structured guidelines for assessing risk in extremist offenders , 2015, Assessment and Development Matters.

[25]  H. M. Trujillo,et al.  Psychometric properties of the Spanish version of the activism and radicalism intention scale / Propiedades psicométricas de la versión española de la escala de intención de activismo y radicalismo , 2016 .

[26]  J. Meloy,et al.  The Clinical Threat Assessment of the Lone-Actor Terrorist. , 2016, The Psychiatric clinics of North America.

[27]  Katarina Jonev.  Cyber terrorism and the use of the internet for terrorist purposes , 2016 .

[28]  Julio César Hernández Castro,et al.  Detecting discussion communities on vaccination in twitter , 2017, Future Gener. Comput. Syst..

[29]  Ebroul Izquierdo,et al.  ACM workshop on surreal media and virtual cloning , 2010, ACM Multimedia.

[30]  David Camacho,et al.  A Genetic Graph-Based Clustering Algorithm , 2012, IDEAL.

[31]  Uuf Brajawidagda,et al.  Tweeting propaganda, radicalization and recruitment: Islamic state supporters multi-sided twitter networks , 2015, DG.O.

[32]  Bertjan Doosje,et al.  Determinants of radicalization of Islamic youth in the Netherlands: personal uncertainty, perceived injustice, and perceived group threat , 2013 .

[33]  Laura Huey.  This is Not Your Mother’s Terrorism: Social Media, Online Radicalization and the Practice of Political Jamming , 2015 .

[34]  Antonio González-Pardo,et al.  Using virtual worlds for behaviour clustering-based analysis , 2010, SMVC '10.

[35]  Julio César Hernández Castro,et al.  A Survey of Social Web Mining Applications for Disease Outbreak Detection , 2014, IDC.

[36]  Laura Huey,et al.  #IS_Fangirl: Exploring a New Role for Women in Terrorism , 2016 .

[37]  Shintaro Okazaki,et al.  Extracting Collective Trends from Twitter Using Social-Based Data Mining , 2013, ICCCI.

[38]  David F. Barrero,et al.  A Genetic Graph-Based Approach for Partitional Clustering , 2014, Int. J. Neural Syst..

[39]  Robyn Torok,et al.  Social Media and the Use of Discursive Markers of Online Extremism and Recruitment , 2021, Research Anthology on Religious Impacts on Society.

[40]  Raúl Cajias,et al.  A study on the impact of crowd-based voting schemes in the 'Eurovision' European contest , 2011, WIMS '11.

[41]  Jason J. Jung,et al.  Social big data: Recent achievements and new challenges , 2015, Information Fusion.

[42]  B. Everitt,et al.  Might Depression, Psychosocial Adversity, and Limited Social Assets Explain Vulnerability to and Resistance against Violent Radicalisation? , 2014, PloS one.

[43]  Western Female Migrants to ISIS: Propaganda, Radicalisation, and Recruitment , 2019 .

[44]  David Camacho,et al.  Extracting behavioural models from 2010 FIFA world cup , 2013, J. Syst. Sci. Complex..

[45]  D. Pressman,et al.  Calibrating risk for violent political extremists and terrorists: the VERA 2 structured assessment , 2012 .