arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.19635cs.SIcs.CY
收藏

合成社交媒体影响力实验:基于智能体强化学习的大语言模型机器人

Synthetic Social Media Influence Experimentation via an Agentic Reinforcement Learning Large Language Model Bot

Bailu Jin, Weisi Guo

AI总结:

本研究提出一个结合智能体智能与大语言模型的模拟环境,通过强化学习设计意见领袖,以伦理方式测试特定话题影响机制,发现约束动作空间与自我观察是实现稳定意见领袖生成的关键。

摘要:

理解在线社交平台上公众舆论演化的动态过程,对于理解影响机制和信息的来源至关重要。传统的影响力分析通常分为对个人属性的定性评估(例如,影响力的心理学)和对影响力权力机制的定量评估(例如,社交网络分析)。研究人员面临的一个挑战是现实世界实验的伦理问题以及社会影响力数据的缺乏。在本研究中,我们提供了一个新颖的模拟环境,该环境结合了智能体智能与大语言模型(LLMs),以合乎伦理的方式测试特定话题的影响机制。我们的框架包含能够生成帖子、就特定话题形成观点,并根据讨论结果在社交上相互关注/取消关注的智能体。该模拟允许研究人员观察观点形成以及影响力领袖涌现的演化过程。利用我们自己的框架,我们设计了一个意见领袖,它利用强化学习(RL)来调整其与社区的语言互动,以随时间最大化其影响力和关注者数量。我们目前的研究结果表明,约束动作空间并结合自我观察是实现在特定话题影响力上稳定且一致的意见领袖生成的关键因素。这证明了该模拟框架能够创建适应复杂且不可预测的社会动态的智能体。这项工作在在线影响力对社会态度和新兴技术影响日益增强的时代具有重要意义。

英文摘要:

Understanding the dynamics of public opinion evolution on online social platforms is crucial for understanding influence mechanisms and the provenance of information. Traditional influence analysis is typically divided into qualitative assessments of personal attributes (e.g., psychology of influence) and quantitative evaluations of influence power mechanisms (e.g., social network analysis). One challenge faced by researchers is the ethics of real-world experimentation and the lack of social influence data. In this study, we provide a novel simulated environment that combines agentic intelligence with Large Language Models (LLMs) to test topic-specific influence mechanisms ethically. Our framework contains agents that generate posts, form opinions on specific topics, and socially follow/unfollow each other based on the outcome of discussions. This simulation allows researchers to observe the evolution of how opinions form and how influence leaders emerge. Using our own framework, we design an opinion leader that utilizes Reinforcement Learning (RL) to adapt its linguistic interaction with the community to maximize its influence and followers over time. Our current findings reveal that constraining the action space and incorporating self-observation are key factors for achieving stable and consistent opinion leader generation for topic-specific influence. This demonstrates the simulation framework's capacity to create agents that can adapt to complex and unpredictable social dynamics. The work is important in an age of increasing online influence on social attitudes and emerging technologies.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑