Agent-based simulation of online social networks and disinformation

TL;DR

This paper introduces a realistic, explainable agent-based simulation framework for online social networks that models social interactions and disinformation campaigns, aiding research on information dynamics.

Contribution

It presents a novel simulation framework combining demographic-based agents, LLM-generated content, and disinformation workflows for realistic and interpretable social network modeling.

Findings

Synthetic networks exhibit realistic topology and behavior.

LLM-generated posts align with agent profiles and memory.

Framework supports studying disinformation effects.

Abstract

Research on online social networks (OSNs) is often hindered by platform opacity, limited access to data, and ethical constraints. Simulation offer a valuable alternative, but existing frameworks frequently lack realism and explainability. This paper presents a simulation framework that models synthetic social networks with agents endowed with demographic-based personality traits and finite-state behavioral automata, enabling realistic and interpretable actions. A generative module powered by a large language model (LLM) produces context-aware social media posts consistent with each agent's profile and memory. In parallel, a red module implements DISARM-inspired workflows to orchestrate disinformation campaigns executed by malicious agents targeting simulated audiences. A Mastodon-based visualization layer supports real-time inspection and post-hoc validation of agent activity within a familiar interface. We evaluate the resulting synthetic social networks using topological metrics and LLM-based content assessments, demonstrating structural, behavioral, and linguistic realism. Overall, the framework enables the creation of customizable and controllable social network environments for studying information dynamics and the effects of disinformation.