发表机构
Institut Polytechnique de Paris, Télécom Paris; University of Salerno; University of Kentucky; Kyung Hee University（巴黎综合理工学院，巴黎电信; 萨莱诺大学; 肯塔基大学; 庆熙大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出基于数字孪生的生成式LLM框架，克隆真实Twitter网络并利用Mistral-7B模拟意见动态，在COVID-19和2020美国选举数据集上显著降低预测误差，提升结构对齐和极化动态再现能力。
AI 中文摘要
社交网络中意见动态的研究是计算社会科学的关键挑战之一，与理解政治极化、错误信息和健康响应直接相关。当前方法侧重于简化的数学模型，这些模型忽略了与信念更新相关的语言和上下文因素，或者使用未经真实数据验证的基于大型语言模型（LLM）的模拟。我们提出了一个基于数字孪生概念的框架，用于模拟社交网络中的意见动态。该方法通过克隆真实的Twitter网络来填补这一空白，为智能体分配一组属性（如人格、情绪、中心性、固执性和影响力），并采用Mistral-7B基于记忆和社会暴露执行意见更新。为评估所提方法，我们针对两个真实的Twitter数据集（COVID-19话语和2020年美国选举）进行了验证。结果表明，所提框架再现意见轨迹的能力将个体预测误差相比最佳经典基线降低了超过50%（Mistral-7B在COVID-19和美国2020年选举数据集上分别实现了平均绝对误差（MAE）=0.150和0.121）。我们在两个数据集上分别观察到结构对齐（Delta_r = 0.120和0.180）和极化动态（Delta_Var = 0.106和0.115）的类似改进。此外，消融研究证实，智能体属性、记忆和社会暴露均有助于框架在再现意见轨迹方面的预测保真度，其中智能体属性是最关键的贡献因素。总体而言，我们的结果表明，将Mistral-7B置于经验克隆的交互网络中，产生了一个能够再现复杂社会动态的现实模拟框架。
英文摘要
The study of opinion dynamics in social networks is one of the key challenges in computational social science with direct relevance to understanding political polarization, misinformation, and health responses. Current approaches focus on simplified mathematical models that ignore linguistic and contextual factors related to belief updates or use Large Language Model (LLM)-based simulations that have not been validated against real data. We present a framework based on the concept of a digital twin to simulate opinion dynamics in social networks. The approach fills the gap by cloning a real-world Twitter network, assigns a set of attributes for agents (such as persona, emotions, centrality, stubbornness, and influence), and employs Mistral-7B to perform opinion update based on memory and social exposure. To evaluate the proposed approach, we validate it against two real Twitter datasets (COVID-19 discourse and U.S elections 2020). The results show that the capability of the proposed framework reproduces opinion trajectories and reduces individual prediction error by more than 50% compared to the best-performing classical baseline (Mistral-7B achieves Mean Absolute Error (MAE) = 0.150 and 0.121 on the COVID-19 and US Election 2020 datasets, respectively). We observe similar improvements in structural alignment (Delta_r = 0.120 and 0.180) and polarization dynamics (Delta_Var = 0.106 and 0.115) on the two datasets, respectively. Additionally, the ablation studies confirm that agent attributes, memory, and social exposure all contribute to the framework's predictive fidelity in reproducing opinion trajectories, with agent attributes being the most critical contributor. Overall, our results demonstrate that grounding Mistral-7B within empirically cloned interaction networks produces a realistic simulation framework capable of reproducing complex social dynamics.
