Opinion Dynamics

Follow this topic Ask about this topic

Opinion dynamics asks how individual beliefs change through social influence, and how those changes shape outcomes such as consensus, polarization, misinformation, and collective decisions. Classical approaches include DeGroot and Friedkin–Johnsen models, bounded-confidence and voter models, and statistical-physics analyses of networked agents. Researchers also study real online discussions and use agent-based or large-language-model simulations to test how network structure, memory, personality, and persuasion affect belief change. A central challenge is distinguishing genuine, accurate agreement from conformity or shared bias, while ensuring simulations reproduce human behavior across different groups and settings.

Latest papers

79 papers5 papers in the last four weeks, down 67% on the four weeks before. 0.0% of all new papers.

Collective Opinion Dynamics in Structured LLM Populations
Apr 13, 2026Erica Cau, Andrea Failla, Giulio RossettiMulti-Agent LLM Systems Opinion Dynamics
Department of Computer Science, University of Pisa · ISTI-CNR
Decentralized Opinion-Integrated Decision making at Unsignalized Intersections via Signed Networks
Apr 10, 2026Bhaskar Varma, Ying Shuai Quan, Karl D. von Ellenrieder +1Multi-Agent Coordination Intelligent Transportation Systems
Faculty of Engineering, Free University of Bozen-Bolzano, Italy · Mechatronics Group, Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden
Talk2AI: A Longitudinal Dataset of Human--AI Persuasive Conversations
Apr 6, 2026Alexis Carrillo, Enrique Taietta, Ali Aghazadeh Ardebili +2Persuasion in Language Models Human-AI Interaction
CogNosco Lab, Department of Psychology and Cognitive Science, University of Trento, Rovereto, Italy. · Department of Sociology and Social Research, University of Trento, Trento, Italy. · Centre for Behavioural and Implementation Sciences in Medicine (BISI), Yong Loo Lin School of Medicine, National University of Singapore, Singapore.
Free Information Disrupts Even Bayesian Crowds
Apr 2, 2026Jonas Stein, Shannon Cruz, Davide Grossi +1Information Flow Control Opinion Dynamics
Faculty of Behavioural and Social Sciences, University of Groningen, The Netherlands. · Department of Communication Arts and Sciences, The Pennsylvania State University, USA · Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen; Amsterdam Center for Law & Economics, University of Amsterdam; Institute for Logic, Language and Computation, University of Amsterdam, The Netherlands. +1
Persona-Based Simulation of Human Opinion at Population Scale
Mar 28, 2026Mao Li, Frederick G. ConradHuman Behavior Simulation Large Language Model-Based Social Simulation
Institute for Social Research, University of Michigan, 426 Thompson St., Ann Arbor, 48104, MI, US.
Beyond Preset Identities: Selective Stance Accommodation and Interaction Reorganisation in Generative Agent Societies
Mar 24, 2026Hanzhong Zhang, Siyang Song, Lu Liu +1Large Language Model-Based Social Simulation Multi-Agent Communication
Department of Computer Science, University of Exeter, Exeter, United Kingdom · Department of Data Science, William & Mary, Williamsburg, Virginia, United States
The Hidden Puppet Master: Predicting Human Belief Change in Manipulative LLM Dialogues
Mar 21, 2026Jocelyn Shen, Amina Luvsanchultem, Jessica Kim +6Opinion Dynamics Language Model Safety Evaluation
♣Massachusetts Institute of Technology, Cambridge, MA, USA · ♢Carnegie Mellon University, Pittsburgh, PA, USA
Subjective-Graph LLM Agents for Simulating Uncertainty in Classroom Social Perception
Mar 21, 2026Jinming Yang, Xinyu Jiang, Xinshan Jiao +1Multi-Agent LLM Systems Opinion Dynamics
Complex Lab, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China · Department of Computer Science, City University of Hong Kong, Hong Kong · School of Health and Medical Technology, Chengdu Neusoft University, Chengdu,2026 China
Reactive Writers: How Co-Writing with AI Changes How We Engage with Ideas
Mar 11, 2026Advait Bhat, Marianne Aubin Le Quéré, Mor Naaman +1Human-AI Co-Creation Opinion Dynamics
Paul G. Allen School of Computer Science, University of Washington · Center for Information Technology Policy, Princeton University · Cornell Tech +1
Examining the Role of YouTube Production and Consumption Dynamics on the Formation of Extreme Ideologies
Mar 9, 2026Sarmad Chandio, Rishab NithyanandOpinion Dynamics Social Media Analysis
University of Iowa
The effect of a toroidal opinion space on opinion bi-polarisation
Mar 5, 2026Frank P. Pijpers, Benedikt V. Meylahn, Michel R. H. MandjesOpinion Dynamics Agent-Based Modeling
Statistics Netherlands The Hague · Korteweg-de Vries Institute for Mathematics University of Amsterdam Amsterdam · Institute of Physics Dutch Institute for Emergent Phenomena University of Amsterdam Amsterdam +1
Credibility Governance: A Social Mechanism for Collective Self-Correction under Weak Truth Signals
Mar 3, 2026Wanying He, Yanxi Lin, Ziheng Zhou +5Shared Decision-Making Opinion Dynamics
School of Artificial Intelligence, Wuhan University; BIGAI Wuhan, China · Tsinghua University Beijing, China · University of California, Los Angeles Los Angeles, US +2
PACIFIER: Pacing Opinion Depolarization via a Unified Graph Learning Framework
Feb 23, 2026Mingkai Liao, Zijun Zhang, Mingyang ZhouSocial Network Analysis Social Media Analysis
Shenzhen University, Shenzhen, China · Hubei University of Police, Wuhan, China
Graph-theoretic Agreement Framework for Multi-agent LLM Systems
Feb 23, 2026Muhammad Umar JavedMulti-Agent LLM Systems Multi-Agent Consensus
The geometry of online conversations and the causal antecedents of conflictual discourse
Feb 17, 2026Carlo Santagiustina, Caterina CrucianiOpinion Dynamics
Inria, France · Sciences Po médialab, France · Venice School of Management, Ca’ Foscari University of Venice, Italy
Grounded Laplacians of Directed Signed Matrix-Weighted Networks: Spectral Properties and Applications to Non-Trivial Consensus
Feb 12, 2026Tianmu Niu, Bing Mao, Hao Liao +2Multi-Agent Coordination Opinion Dynamics
Generating consensus and dissent on massive discussion platforms with a semantic-vector model
Jan 20, 2026A. Ferrer, D. Muñoz-Jordán, A. Rivero +3Opinion Dynamics Computational Social Science
Instituto de Biocomputación y Física de Sistemas Complejos (BIFI), Universidad de Zaragoza, 50018 Zaragoza, Spain · Kampal Data Solutions, WTCZ, Avda. Maria Zambrano 31, 50018 Zaragoza, Spain · Departamento de Física Teórica, Universidad de Zaragoza, 50009 Zaragoza, Spain +2
DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents
Oct 29, 2025Yun-Shiuan Chuang, Ruixuan Tu, Chengtao Dai +9Opinion Dynamics Large Language Model-Based Social Simulation
University of Wisconsin–Madison · Google DeepMind · Stanford University
The price of uncertainty for social consensus
Aug 24, 2025Yunzhe Bai, Alec SunOpinion Dynamics Multi-Agent Consensus

Apr 13, 2026J/K move · Enter open · S save

Collective Opinion Dynamics in Structured LLM Populations

Erica Cau, Andrea Failla, Giulio Rossetti

Department of Computer Science, University of Pisa · ISTI-CNR

Multi-Agent LLM Systems Opinion Dynamics Multi-Agent Debate Agent-Based Modeling

Open paper AskPDF arXiv

Large Language Models are increasingly deployed as interacting agents in settings such as online platforms, recommendation systems, and multi-agent applications. Understanding the collective behaviors that emerge from their interactions is therefore increasingly crucial, especially as these behaviors may shape public opinion and contribute to polarization. In this work, we investigate how network structure and group composition shape the evolution of opinions in populations of LLM agents engaged in multi-round debates. We generate networks with controlled levels of homophily and varying group sizes, and perform ten independent runs per configuration. The results show that LLM agents exhibit patterns that are highly sensitive to network structure, relative group sizes, and to the model itself. We highlight that even within LLM populations, low homophily facilitates convergence by increasing opportunities for cross-group interaction, whereas higher homophily limits cross-group exposure and can preserve distinct opinion states, consistent with previous research. We further show that the choice of LLM substantially affects the resulting dynamics, with different models exhibiting different patterns of opinion updating under comparable network conditions. At the individual level, providing agents with information about their local neighborhood further modulates opinion transitions, revealing substantial differences between models in their sensitivity to local social context. Overall, our findings show that the collective dynamics of LLM populations arise from interactions among model-specific behavior, network structure, population composition, and local social information.