Crowd: A Social Network Simulation Framework

2024-12-14

arXiv.org

AI Summary

Existing general-purpose agent-based modeling and simulation (ABMS) frameworks lack native support for social network structures, resulting in high development costs and poor scalability for complex social simulations. This paper introduces the first lightweight, social-network-oriented ABMS framework, enabling zero-code YAML configuration, generative agent modeling, interactive visualization (via Matplotlib/Plotly), and seamless integration with NetworkX, scikit-learn, and TensorFlow. Its key contributions are: (i) the first extensible ABMS architecture explicitly designed for social network topologies; (ii) the integration of generative agents with dynamic diffusion mechanisms to capture evolving behavioral and structural dynamics; and (iii) end-to-end modeling-to-deployment in minutes and real-time simulation capability. The framework is empirically validated across three canonical scenarios—epidemic propagation, influence maximization, and networked trust games—demonstrating over fivefold improvement in development efficiency while preserving modeling fidelity and analytical expressiveness.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Application Domains: Social Networks

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

To observe how individual behavior shapes a larger community's actions, agent-based modeling and simulation (ABMS) has been widely adopted by researchers in social sciences, economics, and epidemiology. While simulations can be run on general-purpose ABMS frameworks, these tools are not specifically designed for social networks and, therefore, provide limited features, increasing the effort required for complex simulations. In this paper, we introduce Crowd, a social network simulator that adopts the agent-based modeling methodology to model real-world phenomena within a network environment. Designed to facilitate easy and quick modeling, Crowd supports simulation setup through YAML configuration and enables further customization with user-defined methods. Other features include no-code simulations for diffusion tasks, interactive visualizations, data aggregation, and chart drawing facilities. Designed in Python, Crowd also supports generative agents and connects easily with Python's libraries for data analysis and machine learning. Finally, we include three case studies to illustrate the use of the framework, including generative agents in epidemics, influence maximization, and networked trust games.

Problem

• Lack of specialized ABMS tools for social network simulations
• High effort needed for complex social network modeling
• Limited features in general-purpose ABMS frameworks

Innovation

• Agent-based modeling for social networks
• YAML configuration for easy setup
• Python integration for data analysis