Zobrazit v EDS

LLM-AIDSim: LLM-Enhanced Agent-Based Influence Diffusion Simulation in Social Networks

Uloženo v:
Podrobná bibliografie
Název: LLM-AIDSim: LLM-Enhanced Agent-Based Influence Diffusion Simulation in Social Networks
Autoři: Lan Zhang, Yuxuan Hu, Weihua Li, Quan Bai, Parma Nand
Zdroj: Systems ; Volume 13 ; Issue 1 ; Pages: 29
Informace o vydavateli: Multidisciplinary Digital Publishing Institute
Rok vydání: 2025
Sbírka: MDPI Open Access Publishing
Témata: influence diffusion, LLM-enhanced social simulation, topic evolution, agent-based modelling
Popis: This paper introduces an LLM-Enhanced Agent-Based Influence Diffusion Simulation (LLM-AIDSim) framework that integrates large language models (LLMs) into agent-based modelling to simulate influence diffusion in social networks. The proposed framework enhances traditional influence diffusion models by allowing agents to generate language-level responses, providing deeper insights into user agent interactions. Our framework addresses the limitations of probabilistic models by simulating realistic, context-aware user behaviours in response to public statements. Using real-world news topics, we demonstrate the effectiveness of LLM-AIDSim in simulating topic evolution and tracking user discourse, validating its ability to replicate key aspects of real-world information propagation. Our experimental results highlight the role of influence diffusion in shaping collective discussions, revealing that, over time, diffusion narrows the focus of conversations around a few dominant topics. We further analyse regional differences in topic clustering and diffusion behaviours across three cities, Sydney, Auckland, and Hobart, revealing how demographics, income, and education levels influence topic dominance. This work underscores the potential of LLM-AIDSim as a decision-support tool for strategic communication, enabling organizations to anticipate and understand public sentiment trends.
Druh dokumentu: text
Popis souboru: application/pdf
Jazyk: English
Relation: Complex Systems and Cybernetics; https://dx.doi.org/10.3390/systems13010029
DOI: 10.3390/systems13010029
Dostupnost: https://doi.org/10.3390/systems13010029
Rights: https://creativecommons.org/licenses/by/4.0/
Přístupové číslo: edsbas.9DFA3D3E
Databáze: BASE
Popis
Abstrakt:This paper introduces an LLM-Enhanced Agent-Based Influence Diffusion Simulation (LLM-AIDSim) framework that integrates large language models (LLMs) into agent-based modelling to simulate influence diffusion in social networks. The proposed framework enhances traditional influence diffusion models by allowing agents to generate language-level responses, providing deeper insights into user agent interactions. Our framework addresses the limitations of probabilistic models by simulating realistic, context-aware user behaviours in response to public statements. Using real-world news topics, we demonstrate the effectiveness of LLM-AIDSim in simulating topic evolution and tracking user discourse, validating its ability to replicate key aspects of real-world information propagation. Our experimental results highlight the role of influence diffusion in shaping collective discussions, revealing that, over time, diffusion narrows the focus of conversations around a few dominant topics. We further analyse regional differences in topic clustering and diffusion behaviours across three cities, Sydney, Auckland, and Hobart, revealing how demographics, income, and education levels influence topic dominance. This work underscores the potential of LLM-AIDSim as a decision-support tool for strategic communication, enabling organizations to anticipate and understand public sentiment trends.
DOI:10.3390/systems13010029