Fusing Dynamics Equation: A Social Opinions Prediction Algorithm with LLM-based Agents

Junchi Yao, Hongjie Zhang, Jie Ou, Dingyi Zuo, Zheng Yang, Zhicheng Dong
{"title":"Fusing Dynamics Equation: A Social Opinions Prediction Algorithm with LLM-based Agents","authors":"Junchi Yao, Hongjie Zhang, Jie Ou, Dingyi Zuo, Zheng Yang, Zhicheng Dong","doi":"arxiv-2409.08717","DOIUrl":null,"url":null,"abstract":"In the context where social media is increasingly becoming a significant\nplatform for social movements and the formation of public opinion, accurately\nsimulating and predicting the dynamics of user opinions is of great importance\nfor understanding social phenomena, policy making, and guiding public opinion.\nHowever, existing simulation methods face challenges in capturing the\ncomplexity and dynamics of user behavior. Addressing this issue, this paper\nproposes an innovative simulation method for the dynamics of social media user\nopinions, the FDE-LLM algorithm, which incorporates opinion dynamics and\nepidemic model. This effectively constrains the actions and opinion evolution\nprocess of large language models (LLM), making them more aligned with the real\ncyber world. In particular, the FDE-LLM categorizes users into opinion leaders\nand followers. Opinion leaders are based on LLM role-playing and are\nconstrained by the CA model, while opinion followers are integrated into a\ndynamic system that combines the CA model with the SIR model. This innovative\ndesign significantly improves the accuracy and efficiency of the simulation.\nExperiments were conducted on four real Weibo datasets and validated using the\nopen-source model ChatGLM. The results show that, compared to traditional\nagent-based modeling (ABM) opinion dynamics algorithms and LLM-based opinion\ndiffusion algorithms, our FDE-LLM algorithm demonstrates higher accuracy and\ninterpretability.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Social and Information Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.08717","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

In the context where social media is increasingly becoming a significant platform for social movements and the formation of public opinion, accurately simulating and predicting the dynamics of user opinions is of great importance for understanding social phenomena, policy making, and guiding public opinion. However, existing simulation methods face challenges in capturing the complexity and dynamics of user behavior. Addressing this issue, this paper proposes an innovative simulation method for the dynamics of social media user opinions, the FDE-LLM algorithm, which incorporates opinion dynamics and epidemic model. This effectively constrains the actions and opinion evolution process of large language models (LLM), making them more aligned with the real cyber world. In particular, the FDE-LLM categorizes users into opinion leaders and followers. Opinion leaders are based on LLM role-playing and are constrained by the CA model, while opinion followers are integrated into a dynamic system that combines the CA model with the SIR model. This innovative design significantly improves the accuracy and efficiency of the simulation. Experiments were conducted on four real Weibo datasets and validated using the open-source model ChatGLM. The results show that, compared to traditional agent-based modeling (ABM) opinion dynamics algorithms and LLM-based opinion diffusion algorithms, our FDE-LLM algorithm demonstrates higher accuracy and interpretability.
融合动力学方程:基于 LLM 代理的社会意见预测算法
在社交媒体日益成为社会运动和舆论形成的重要平台的背景下,准确模拟和预测用户意见的动态变化对于理解社会现象、制定政策和引导舆论具有重要意义。然而,现有的模拟方法在捕捉用户行为的复杂性和动态性方面面临挑战。针对这一问题,本文提出了一种创新的社交媒体用户舆论动态模拟方法--FDE-LLM 算法,该算法结合了舆论动态和流行病模型。这有效地约束了大型语言模型(LLM)的行动和观点演变过程,使其更加贴近真实的网络世界。其中,FDE-LLM 将用户分为意见领袖和追随者。意见领袖以 LLM 角色扮演为基础,受到 CA 模型的约束,而意见追随者则被整合到结合了 CA 模型和 SIR 模型的动态系统中。我们在四个真实微博数据集上进行了实验,并使用开源模型 ChatGLM 进行了验证。实验结果表明,与传统的基于代理建模(ABM)的舆情动态算法和基于 LLM 的舆情扩散算法相比,我们的 FDE-LLM 算法具有更高的准确性和可解释性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信