Towards an LLM-powered Social Digital Twinning Platform
Önder Gürcan, Vanja Falck, Markus G. Rousseau, Larissa L. Lima
TL;DR
The paper tackles the need for flexible, accessible social digital twins that can explore policy scenarios without requiring advanced programming. It introduces the Social Digital Twinner, an LLM-enabled agent-based platform comprising a data infrastructure, a four-layer ABMS simulation engine, and a map-based UI that supports natural-language interaction with agents. By leveraging real Norwegian data and a synthetic EU-SILC-based population, the authors demonstrate interactive policy exploration through a Kragerø NEET case study, illustrating how NL queries can reveal agent-specific and aggregate insights. The work also discusses privacy, democratization, and the responsibilities surrounding NL-driven socio-technical simulations, and outlines future directions for empirical evaluation and broader stakeholder adoption.
Abstract
We present Social Digital Twinner, an innovative social simulation tool for exploring plausible effects of what-if scenarios in complex adaptive social systems. The architecture is composed of three seamlessly integrated parts: a data infrastructure featuring real-world data and a multi-dimensionally representative synthetic population of citizens, an LLM-enabled agent-based simulation engine, and a user interface that enable intuitive, natural language interactions with the simulation engine and the artificial agents (i.e. citizens). Social Digital Twinner facilitates real-time engagement and empowers stakeholders to collaboratively design, test, and refine intervention measures. The approach is promoting a data-driven and evidence-based approach to societal problem-solving. We demonstrate the tool's interactive capabilities by addressing the critical issue of youth school dropouts in Kragero, Norway, showcasing its ability to create and execute a dedicated social digital twin using natural language.