The results demonstrate that grounding Mistral-7B within empirically cloned interaction networks produces a realistic simulation framework capable of reproducing complex social dynamics.
Abstract
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.
Understanding the dynamics of stance change on social media is crucial for addressing polarization and information integrity, yet observational studies face challenges including limited experimental control, restricted data access, and algorithmic confounds. We leverage Generative Agent-Based Modeling (GABM)—a novel si...
Valerio La Gatta, Gian Marco Orlando, Marco Perillo et al.· Proceedings of the 37th ACM...· 1 citation
TSN4PI, a unified framework for tracking the evolution of political ideologies on social media, includes two core modules: the PIDN and the PIPN, which employs temporal graph neural networks to predict future ideological shifts, enabling comprehensive analysis of ideology presence, intensity, and evolution.
This survey presents the first comprehensive review of LLMs for social network modeling by organizing the literature into two broad categories: network generative models and dynamic process models.
Shikha Mallick, Alex Thomo, A. Saxena· 0 citations
Understanding how sustainable behaviors spread within heterogeneous societies requires the integration of behavioral data, social influence mechanisms, and structured control strategies. In this article, we propose a data-driven computational framework for coupled opinion-adoption dynamics in social systems. Each node...
Martina Alutto, S. Bellotti, Fabrizio Dabbene et al.· IEEE Transactions on Computa...· 1 citation
A visualization analysis framework based on multi-source data perception and dynamic graph inference that effectively reveals the black-box characteristics of discourse dissemination and provides data support for precise ideological and political communication guidance is constructed.
Jing Yang· Advanced Electromagnetics· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026