[PODCAST] Polarization 2.0: How political debates evolve over time on social networks

How do political debates change over time to the point of polarizing the opinion of an entire population? To what extent can the influence of recommendation systems can appease or inflame user exchanges on social networks?

An interdisciplinary team combining the expertise of researchers in computer science and political science has formed around the ANR Boom* project, with the aim of contributing to a better understanding of the phenomenon of polarization. Team members include Célina Treuillier (doctoral student in computer science at Loria), Sylvain Castagnos (senior lecturer in computer science at the University of Lorraine and researcher at Loria), Christèle Lagier (Senior Lecturer in Political Science at the University of Avignon) and Armelle Brun (Professor in Computer Science at the University of Lorraine and researcher at Loria) published in April 2024, the article “Gaining a better understanding of online polarization by approaching it as a dynamic process” in Scientific Reports (Nature).

In this article, they analyze the evolution of behaviors observed around a mature political debate, versus those observed in an emerging political debate. Based on this comparison, they identify the characteristic periods of the phenomenon, demonstrating that the polarization process is dynamic.

Find out more in this podcast (only available in French-speaking version).