Dissertation
"On Meta-Networks, Deep Learning, Time and Jihadism"
Update, August 2021: My Ph.D. thesis has been selected as the runner-up finalist in the 2019-2020 Terrorism Research Initiative prize for the best doctoral thesis in the field of Terrorism and Counter-terrorism. Read the official announcement here: https://www.universiteitleiden.nl/binaries/content/assets/customsites/perspectives-on-terrorism/2021/issue-4/tri-theses-award.pdf
Read the thesis at https://www.researchgate.net/publication/339254207_On_Meta-Networks_Deep_Learning_Time_and_Jihadism
ABSTRACT
Jihadist terrorism represents a global threat for society and a challenge for scientists interested in understanding its complexity. This complexity continuously calls for developments in the ways in which terrorism is studied. Enhancing the empirical knowledge on the phenomenon can potentially contribute to develop concrete real-world applications and, ultimately, to the prevention of societal damages. Taking these aspects into consideration, this work presents a novel methodological framework that integrates network science and deep learning with the aim to shed light on jihadism, both at the explanatory and predictive levels. Specifically, this dissertation will compare and analyze the world's most active jihadist terrorist organizations (i.e. The Islamic State, the Taliban, Al Qaeda, Boko Haram, and Al Shabaab) to investigate their behavioral patterns and forecast their future actions. The analyses will employ hybrid techniques and pursue three linked aims. Firstly, using stochastic transition matrices to detect complex recurring behaviors in jihadist operational dynamics and presenting Normalized Transition Similarity, a novel coefficient of pairwise similarity in terms of strategic choices. Secondly, applying Hawkes point processes to investigate the presence of time-dependent structure in attack sequences. Thirdly, integrate complex meta-networks and deep learning to rank and forecast most probable future targets. This research seeks to reveal how hidden abstract connections between events may be exploited to unfold jihadist temporal mechanics and how memory-like processes (i.e., multiple non-random parallel and interconnected recurrent behaviors) can illuminate the way in which these groups act.
CONTENTS
INTRODUCTION
BACKGROUND
What is terrorism?
Theoretical framework
MOTIVATIONS AND AIMS
Aim of the work
On the need for rethinking research in criminology and terrorism
CASE STUDIES AND DATA
Jihadist terrorism: concepts and actors
Data
TRANSITION NETWORKS OF JIHADISM
Introduction
Data Processing
Stochastic Transition Matrices
Normalized Transition Similarity
Conclusions and Future Work
HAWKES PROCESSES OF JIHADISM
Introduction
Related work
Mathematical framework
Experiments
Discussion and Future Work
DEEP LEARNING AND TERRORISM: RECURRENT NEURAL NETWORKS FOR TARGET FORECASTING
Introduction
Background
Methodological Framework
On the properties of time series of jihadist groups
Results of the models
Overcoming issues on weak and rare signals
What is this all about? Notes to potential critiques
Discussion and future work
CONCLUDING REMARKS