Advancing Conflict Research Through Computational Approaches

Abstract

Conflict, from small-scale verbal disputes to large-scale violent war between nations, is one of the most fundamental elements of social life and a central topic in social science research. The main argument of this book is that computational approaches have enormous potential to advance conflict research, e.g., by making use of the ever-growing computer processing power to model complex conflict dynamics, by drawing on innovative methods from simulation to machine learning, and by building on vast quantities of conflict-related data that emerge at unprecedented scale in the digital age. Our goal is (a) to demonstrate how such computational approaches can be used to improve our understanding of conflict at any scale and (b) to call for the consolidation of computational conflict research as a unified field of research that collectively aims to gather such insights. We first give an overview of how various computational approaches have already impacted on conflict research and then guide through the different chapters that form part of this book. Finally, we propose to map the field of computational conflict research by positioning studies in a two-dimensional space depending on the intensity of the analyzed conflict and the chosen computational approach.

Game-theoretic agent-based modelling of micro-level conflict: Evidence from the ISIS-Kurdish war

“…Computational models dealing with international security have recently emerged within the field of conflict studies (see for example [ 28 ]). Statistical models had until now dominated the field [ 29 ]; while these are valuable in understanding causal dynamics and the relationship between variables, their application is generally restricted to understanding the causes of conflict [ 30 – 32 ] and forecasting violent outbreaks [ 33 – 37 ].…”

Promises and pitfalls of computational modelling for insurgency conflicts

“…An advantage of the application of computational models is the ability to analyze the effects of military strategies ex-ante, and hence before they are used in practice. 4 For example, Chaturvedi et al 5 demonstrated the capability of agent-based modeling (ABM) to analyze the interactions of government, firms, and adversaries in (potential) information warfare scenarios. While an increased amount of available data promised a quick development of predictive models for emerging insurgent conflicts, machine learning techniques have been unable to fulfill the promise to deliver early-warning systems.…”

Untitled

“…Computational models dealing with international security have recently emerged within the field of conflict studies (see for example [28]). Statistical models had until now dominated the field [29]; while these are valuable in understanding causal dynamics and the relationship between variables, their application is generally restricted to understanding the causes of conflict [30][31][32] and forecasting violent outbreaks [33][34][35][36][37].…”