GA-S$^3$: Comprehensive Social Network Simulation with Group Agents

TL;DR

This paper introduces GA-S$^3$, a social network simulation system using group agents to model large-scale online social phenomena efficiently, validated by a new benchmark and real-world data.

Contribution

The paper presents a novel social network simulation system with group agents and a new benchmark, enabling realistic large-scale social network modeling.

Findings

Accurately predicts social network phenomena

Efficiently models large-scale interactions

Provides a new benchmark for social network analysis

Abstract

Social network simulation is developed to provide a comprehensive understanding of social networks in the real world, which can be leveraged for a wide range of applications such as group behavior emergence, policy optimization, and business strategy development. However, billions of individuals and their evolving interactions involved in social networks pose challenges in accurately reflecting real-world complexities. In this study, we propose a comprehensive Social Network Simulation System (GA-S3) that leverages newly designed Group Agents to make intelligent decisions regarding various online events. Unlike other intelligent agents that represent an individual entity, our group agents model a collection of individuals exhibiting similar behaviors, facilitating the simulation of large-scale network phenomena with complex interactions at a manageable computational cost. Additionally, we have constructed a social network benchmark from 2024 popular online events that contains fine-grained information on Internet traffic variations. The experiment demonstrates that our approach is capable of achieving accurate and highly realistic prediction results. Code is open at https://github.com/AI4SS/GAS-3.