LLM-AIDSim: LLM-Enhanced Agent-Based Influence Diffusion Simulation in Social Networks
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 b...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Systems |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-8954/13/1/29 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587417203245056 |
|---|---|
| author | Lan Zhang Yuxuan Hu Weihua Li Quan Bai Parma Nand |
| author_facet | Lan Zhang Yuxuan Hu Weihua Li Quan Bai Parma Nand |
| author_sort | Lan Zhang |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-3793ccf5383043518e8eb4a608d9754e |
| institution | Kabale University |
| issn | 2079-8954 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Systems |
| spelling | doaj-art-3793ccf5383043518e8eb4a608d9754e2025-01-24T13:50:32ZengMDPI AGSystems2079-89542025-01-011312910.3390/systems13010029LLM-AIDSim: LLM-Enhanced Agent-Based Influence Diffusion Simulation in Social NetworksLan Zhang0Yuxuan Hu1Weihua Li2Quan Bai3Parma Nand4School of Engineering, Computer & Mathematical Sciences, Auckland University of Technology, Auckland 1010, New ZealandSchool of Information and Communication Technology, University of Tasmania, Hobart, TAS 7001, AustraliaSchool of Engineering, Computer & Mathematical Sciences, Auckland University of Technology, Auckland 1010, New ZealandSchool of Information and Communication Technology, University of Tasmania, Hobart, TAS 7001, AustraliaSchool of Engineering, Computer & Mathematical Sciences, Auckland University of Technology, Auckland 1010, New ZealandThis 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.https://www.mdpi.com/2079-8954/13/1/29influence diffusionLLM-enhanced social simulationtopic evolutionagent-based modelling |
| spellingShingle | Lan Zhang Yuxuan Hu Weihua Li Quan Bai Parma Nand LLM-AIDSim: LLM-Enhanced Agent-Based Influence Diffusion Simulation in Social Networks Systems influence diffusion LLM-enhanced social simulation topic evolution agent-based modelling |
| title | LLM-AIDSim: LLM-Enhanced Agent-Based Influence Diffusion Simulation in Social Networks |
| title_full | LLM-AIDSim: LLM-Enhanced Agent-Based Influence Diffusion Simulation in Social Networks |
| title_fullStr | LLM-AIDSim: LLM-Enhanced Agent-Based Influence Diffusion Simulation in Social Networks |
| title_full_unstemmed | LLM-AIDSim: LLM-Enhanced Agent-Based Influence Diffusion Simulation in Social Networks |
| title_short | LLM-AIDSim: LLM-Enhanced Agent-Based Influence Diffusion Simulation in Social Networks |
| title_sort | llm aidsim llm enhanced agent based influence diffusion simulation in social networks |
| topic | influence diffusion LLM-enhanced social simulation topic evolution agent-based modelling |
| url | https://www.mdpi.com/2079-8954/13/1/29 |
| work_keys_str_mv | AT lanzhang llmaidsimllmenhancedagentbasedinfluencediffusionsimulationinsocialnetworks AT yuxuanhu llmaidsimllmenhancedagentbasedinfluencediffusionsimulationinsocialnetworks AT weihuali llmaidsimllmenhancedagentbasedinfluencediffusionsimulationinsocialnetworks AT quanbai llmaidsimllmenhancedagentbasedinfluencediffusionsimulationinsocialnetworks AT parmanand llmaidsimllmenhancedagentbasedinfluencediffusionsimulationinsocialnetworks |