S$^3$: Social-network Simulation System with Large Language Model-Empowered Agents

TL;DR

This paper introduces S$^3$, a social network simulation system utilizing large language model-powered agents that emulate human behaviors, enabling realistic simulation of social phenomena with promising accuracy, and opening new avenues for social science research.

Contribution

The work pioneers the integration of LLMs into social network simulation, employing prompt engineering to create agents that realistically emulate human emotions, attitudes, and interactions.

Findings

Agents successfully emulate human-like behaviors in social networks.

Simulation results align with real-world social phenomena.

The system demonstrates promising accuracy in population-level predictions.

Abstract

Social network simulation plays a crucial role in addressing various challenges within social science. It offers extensive applications such as state prediction, phenomena explanation, and policy-making support, among others. In this work, we harness the formidable human-like capabilities exhibited by large language models (LLMs) in sensing, reasoning, and behaving, and utilize these qualities to construct the S$^3$ system (short for $\textbf{S}$ocial network $\textbf{S}$imulation $\textbf{S}$ystem). Adhering to the widely employed agent-based simulation paradigm, we employ prompt engineering and prompt tuning techniques to ensure that the agent's behavior closely emulates that of a genuine human within the social network. Specifically, we simulate three pivotal aspects: emotion, attitude, and interaction behaviors. By endowing the agent in the system with the ability to perceive the informational environment and emulate human actions, we observe the emergence of population-level phenomena, including the propagation of information, attitudes, and emotions. We conduct an evaluation encompassing two levels of simulation, employing real-world social network data. Encouragingly, the results demonstrate promising accuracy. This work represents an initial step in the realm of social network simulation empowered by LLM-based agents. We anticipate that our endeavors will serve as a source of inspiration for the development of simulation systems within, but not limited to, social science.