Published in arXiv preprint arXiv:2607.13693, 2026
This chapter reviews the evolution of social simulation from classical agent-based models to AI-enhanced digital twins.
Recommended citation: Cau, E., Failla, A., Pansanella, V., & Rossetti, G. (2026). "Social Simulations: from Agent-Based Modeling to Digital Twins." arXiv preprint arXiv:2607.13693.
Download Paper | Download Slides
Published in Handbook of Human-AI Collaboration, 2026
This chapter connects research on representation biases in large language models with theory-of-mind capabilities.
Recommended citation: Rossetti, G., Abramski, K., Cau, E., Pansanella, V., & Stella, M. (2026). "LLMs and Cognition: From Representation Biases to a Theory of Mind." In Handbook of Human-AI Collaboration (pp. 1-39). Springer Nature Switzerland.
Download Paper | Download Slides
Published in arXiv preprint arXiv:2604.11312, 2026
This paper studies how network structure affects opinion dynamics and agreement drift in debates among LLM agents.
Recommended citation: Cau, E., Failla, A., & Rossetti, G. (2026). "Network Effects and Agreement Drift in LLM Debates." arXiv preprint arXiv:2604.11312.
Download Paper | Download Slides
Published in Big Data & Society, 2026
This paper presents Y Social, an LLM-powered digital twin of social media designed to simulate online interactions and study complex social phenomena.
Recommended citation: Rossetti, G., Stella, M., Cazabet, R., Abramski, K., Citraro, S., Cau, E., Failla, A., Morini, V., & Pansanella, V. (2026). "YSocial: An artificial intelligence powered social media virtual twin." Big Data & Society, 13(3), 20539517261431576.
Download Paper | Download Slides
Published in EPJ Data Science, 2025
This paper investigates opinion dynamics in LLM interactions, showing that models exhibit selective agreement rather than simple sycophancy.
Recommended citation: Cau, E., Pansanella, V., Pedreschi, D., & Rossetti, G. (2025). "Selective agreement, not sycophancy: investigating opinion dynamics in LLM interactions." EPJ Data Science, 14(1), 59.
Download Paper | Download Slides
Published in arXiv preprint arXiv:2502.19098, 2025
This paper introduces a language-driven opinion dynamics model for agent-based simulations with large language models.
Recommended citation: Cau, E., Pansanella, V., Pedreschi, D., & Rossetti, G. (2025). "Language-Driven Opinion Dynamics in Agent-Based Simulations with LLMs." arXiv preprint arXiv:2502.19098.
Download Paper | Download Slides
Published in arXiv preprint arXiv:2403.14298, 2024
This paper examines how human and artificial-intelligence biases affect online discussion spaces.
Recommended citation: Morini, V., Pansanella, V., Abramski, K., Cau, E., Failla, A., Citraro, S., & Rossetti, G. (2024). "From Perils to Possibilities: Understanding how Human (and AI) Biases affect Online Fora." arXiv preprint arXiv:2403.14298.
Download Paper | Download Slides
Published in PLOS Complex Systems, 2024
This paper analyzes echo chambers’ structural stability and the role of in-group attitudes in shaping online discussions.
Recommended citation: Cau, E., Morini, V., & Rossetti, G. (2024). "Trends and topics: Characterizing echo chambers’ topological stability and in-group attitudes." PLOS Complex Systems, 1(2), e0000008.
Download Paper | Download Slides
Published in International Conference on Complex Networks and Their Applications, 2024
This paper investigates how biases interact and evolve in opinion dynamics when simulated with large language models.
Recommended citation: Cau, E., Failla, A., & Rossetti, G. (2024, December). "Bots of a Feather: Mixing Biases in LLMs’ Opinion Dynamics." In International Conference on Complex Networks and Their Applications (pp. 166-176). Cham: Springer Nature Switzerland.
Download Paper | Download Slides
Published in Complex Networks 2023, 2023
A framework for studying the temporal and linguistic evolution of polarized online discussions.
Recommended citation: Cau, E., Morini, V., & Rossetti, G. (2023). "A framework for the diachronic and linguistic analysis of online polarized discussions." In Complex Networks 2023.
Download Paper | Download Slides