Computational Approaches to Digital Political Polarization: Advancing Social Big Data Analysis and Social Network Analysis

The digital public sphere has mutated into a fragmented landscape where algorithmic architectures often accelerate ideological divides. To move beyond descriptive accounts of this phenomenon, contemporary sociology requires rigorous, scalable computational methodologies. Hosted by RC33 Logic and Methodology in Sociology, this session provides an international forum for cutting-edge empirical research that deploys Big Data analytics and Social Network Analysis (SNA) to detect, model, and map digital political polarization.

We invite innovative abstract proposals that leverage high-volume data mining and network metrics to dissect the structural properties of online conflict. The session is highly interested in methodological workflows capable of tracking electoral campaigns, identifying echo chambers, and mapping the attitudes or ideologies of online social network users. We welcome applied works using advanced quantitative and computational methods to study contemporary social processes, including social network analysis, community detection, semantic and discursive networks, computational text analysis, machine learning, artificial intelligence, and large language models (LLM), among others.

By prioritizing robust computational frameworks, this session aims to foster deep interdisciplinary collaboration between data science and political sociology. Ultimately, our goal is to enhance the discipline's analytical and explanatory capacity to understand how interactional structures shape modern democratic crises.