SimSpark: Interactive Simulation of Social Media Behaviors

2025-05-02

Proceedings of the ACM on Human-Computer Interaction

AI Summary

Existing social behavior simulation platforms lack flexibility and controllability, hindering multi-scenario, multi-role user behavior research. To address this, we propose an interactive social platform simulation system featuring: (1) a novel LLM-integrated agent behavior generation mechanism enabling customizable user roles and socio-environmental configurations within a multi-granularity workflow; (2) a real-time parameter tuning interface, human-in-the-loop intervention capability, and multi-dimensional visualization analytics framework; and (3) a hybrid credibility assessment methodology grounded in case-based validation and expert feedback. Rigorous evaluation—including quantitative metrics, scenario-based case studies, and expert interviews—demonstrates significant improvements in behavioral fidelity, configurability across diverse social contexts, and ethical safety. The system provides a reproducible, intervenable experimental infrastructure for social mechanism design and human-AI collaborative research.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Understanding user behaviors on social media has garnered significant scholarly attention, enhancing our comprehension of how virtual platforms impact society and empowering decision-makers. Simulating social media behaviors provides a robust tool for capturing the patterns of social media behaviors, testing hypotheses, and predicting the effects of various interventions, ultimately contributing to a deeper understanding of social media environments. Moreover, it can overcome difficulties associated with utilizing real data for analysis, such as data accessibility issues, ethical concerns, and the complexity of processing large and heterogeneous datasets. However, researchers and stakeholders need more flexible platforms to investigate different user behaviors by simulating different scenarios and characters, which is not possible yet. Therefore, this paper introduces SimSpark, an interactive system including simulation algorithms and interactive visual interfaces which is capable of creating small simulated social media platforms with customizable characters and social environments. We address three key challenges: generating believable behaviors, validating simulation results, and supporting interactive control for generation and results analysis. A simulation workflow is introduced to generate believable behaviors of agents by utilizing large language models. A visual interface enables real-time parameter adjustment and process monitoring for customizing generation settings. A set of visualizations and interactions are also designed to display the models' outputs for further analysis. Effectiveness is evaluated through case studies, quantitative simulation model assessments, and expert interviews.

Problem

• Simulating social media behaviors to understand user patterns and impacts
• Overcoming real data limitations like accessibility and ethical concerns
• Providing flexible platforms for customizable scenario and character simulations

Innovation

• SimSpark simulates social media with customizable characters
• Uses large language models for believable agent behaviors
• Interactive visual interface for real-time adjustments