A Natural Language Agentic Approach to Study Affective Polarization

The repository contains python source code for experiments, created by Stephanie A. Malvicini, reported in the following paper: Malvicini, S. A.; Gajewska, E.; Derbent, A.; Budzynska, K.; Chudziak, J. A. and Martinez, M. V. (2026). A Natural Language Agentic Approach to Study Affective Polarization. In Proceedings of the 18th International Conference on Agents and Artificial Intelligence - Volume 1, ISBN 978-989-758-796-2, ISSN 2184-433X, pages 339-346. Code also available at: https://github.com/ICBD-ICIC/PolarMasSupplementaryMaterial. We would like to acknowledge that the work has been supported in part by the Spanish MCIN/AEI grant PCI2022-135010-2, in part by the Polish National Science Centre, Poland (Chist-Era IV) under grant 2022/04/Y/ ST6/00001, and in part by Universidad Nacional del Sur~(UNS) under grant PGI~24/ZN057.