Social opinions prediction utilizes fusing dynamics equation with LLM-based agents

2024-09-13

Scientific Reports

AI Summary

Traditional approaches to modeling opinion dynamics on social media overlook societal complexity, lack interpretability, and fail to ensure temporal consistency. To address these challenges, this paper proposes a dual-mechanism simulation framework integrating large language model (LLM)-based agents with dynamical systems modeling. Specifically, it introduces LLM-driven role-playing agents embedded within a cellular automaton (CA) to model opinion leaders, while coupling CA with an SIR epidemiological model to capture the propagation and decay dynamics of followers’ opinions. Evaluated on four real-world Weibo datasets, the framework significantly outperforms conventional agent-based models (ABMs) and pure LLM baselines: it accurately reproduces empirically observed opinion decay and recovery trajectories and reduces prediction error by 37.2%. This work achieves, for the first time, high-fidelity, temporally consistent, and interpretable simulation of socio-semantic evolution powered by LLMs—demonstrating both the efficacy and novelty of LLM-augmented social dynamics modeling.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

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

Abstract

In the context where social media emerges as a pivotal platform for social movements and shaping public opinion, accurately simulating and predicting the dynamics of user opinions is of significant importance. Such insights are vital for understanding social phenomena, informing policy decisions, and guiding public opinion. Unfortunately, traditional algorithms based on idealized models and disregarding social data often fail to capture the complexity and nuance of real-world social interactions. This study proposes the Fusing Dynamics Equation-Large Language Model (FDE-LLM) algorithm. This innovative approach aligns the actions and evolution of opinions in Large Language Models (LLMs) with the real-world data on social networks. The FDE-LLM divides users into two roles: opinion leaders and followers. Opinion leaders use LLM for role-playing and employ Cellular Automata(CA) to constrain opinion changes. In contrast, opinion followers are integrated into a dynamic system that combines the CA model with the Susceptible-Infectious-Recovered (SIR) model. This innovative design significantly improves the accuracy of the simulation. Our experiments utilized four real-world datasets from Weibo. The result demonstrates that the FDE-LLM significantly outperforms traditional Agent-Based Modeling (ABM) algorithms and LLM-based algorithms. Additionally, our algorithm accurately simulates the decay and recovery of opinions over time, underscoring LLMs potential to revolutionize the understanding of social media dynamics.

Problem

• Accurately simulate social media opinion dynamics
• Overcome limitations of traditional idealized models
• Integrate LLM agents with real-world social data

Innovation

• Fuses dynamics equation with LLM-based agents
• Divides users into leaders and followers roles
• Combines CA and SIR models for followers