Search papers, labs, and topics across Lattice.
This chapter traces the evolution of social simulation methodologies, transitioning from classical agent-based models with predefined behavioral rules to advanced AI-enhanced simulations utilizing Large Language Models, culminating in the concept of Social Digital Twins. This progression is significant as it reflects a shift towards high-fidelity, data-driven representations of real-world socio-technical systems, enabling more accurate and nuanced analyses of social dynamics. Key findings emphasize the advantages and limitations of each paradigm, illustrating the growing complexity and realism in modeling social interactions.
Social Digital Twins could revolutionize our understanding of socio-technical systems by providing unprecedented realism in social simulations.
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.
