Social Opinions Prediction Utilizes Fusing Dynamics Equation with LLM-based Agents

TL;DR

This paper introduces the FDE-LLM algorithm that combines social network data, cellular automata, and large language models to improve the simulation and prediction of opinion dynamics on social media.

Contribution

The study presents a novel FDE-LLM approach integrating LLMs with social data and CA/SIR models, enhancing accuracy in social opinion prediction.

Findings

FDE-LLM outperforms traditional algorithms in accuracy.

Effectively models opinion decay and recovery.

Validated on four real-world Weibo datasets.

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 devides 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.