Simulating Rumor Spreading in Social Networks using LLM Agents
This addresses the issue of misinformation spread for social media researchers, but it is incremental as it applies existing LLM methods to a new simulation context.
The study tackled the problem of simulating rumor spreading in social networks by using LLM agents, and the result showed that the framework could simulate over 100 agents in networks with thousands of edges, with rumor dissemination affecting up to 83% of agents depending on network structure and agent behaviors.
With the rise of social media, misinformation has become increasingly prevalent, fueled largely by the spread of rumors. This study explores the use of Large Language Model (LLM) agents within a novel framework to simulate and analyze the dynamics of rumor propagation across social networks. To this end, we design a variety of LLM-based agent types and construct four distinct network structures to conduct these simulations. Our framework assesses the effectiveness of different network constructions and agent behaviors in influencing the spread of rumors. Our results demonstrate that the framework can simulate rumor spreading across more than one hundred agents in various networks with thousands of edges. The evaluations indicate that network structure, personas, and spreading schemes can significantly influence rumor dissemination, ranging from no spread to affecting 83\% of agents in iterations, thereby offering a realistic simulation of rumor spread in social networks.