computational social science

Social Simulations: from Agent-Based Modeling to Digital Twins

arXiv:2607.13693

summary

The chapter reviews the progression of social simulation from classical agent‑based models with explicit behavioral rules, through AI‑enhanced simulations using large language models, to high‑fidelity social digital twins that replicate real socio‑technical systems.

Abstract

This book chapter covers the evolution of social simulation from classical agent-based models, in which agents interact according to explicitly defined behavioral rules, to AI-enhanced simulations based on Large Language Models and, ultimately, Social Digital Twins: high-fidelity, data-driven representations of real-world socio-technical systems. Along this trajectory, we discuss the main methodological foundations, applications, advantages, and limitations of each paradigm, highlighting the progressive shift from abstract models designed to investigate general social mechanisms toward increasingly realistic computational representations of specific social systems.

Entry for Encyclopedia of Social Network Analysis and Mining

Topics & keywords

#agent-based modeling#large language models#social digital twins#simulation methods#socio-technical systemsagent-based modelslarge language modelsdigital twinsbehavioral rulesdata-driven simulation