Opinion de-polarization of social networks with GNNs
Konstantinos Mylonas, Thrasyvoulos Spyropoulos
TL;DR
The paper tackles reducing polarization in social networks governed by Friedkin–Johnsen dynamics by identifying a set of $K$ users to moderate. It replaces computationally intensive greedy evaluation with a Graph Neural Network that predicts per-node polarization gains, trained on synthetic two-echo-chamber graphs and evaluated on real networks. The resulting GNN-GreedyExt achieves speedups up to $16\times$ while maintaining about 95% of GreedyExt's depolarization performance, demonstrating scalable depolarization for large graphs. This approach enables practical intervention strategies to mitigate echo chambers without sacrificing much effectiveness.
Abstract
Nowadays, social media is the ground for political debate and exchange of opinions. There is a significant amount of research that suggests that social media are highly polarized. A phenomenon that is commonly observed is the echo chamber structure, where users are organized in polarized communities and form connections only with similar-minded individuals, limiting themselves to consume specific content. In this paper we explore a way to decrease the polarization of networks with two echo chambers. Particularly, we observe that if some users adopt a moderate opinion about a topic, the polarization of the network decreases. Based on this observation, we propose an efficient algorithm to identify a good set of K users, such that if they adopt a moderate stance around a topic, the polarization is minimized. Our algorithm employs a Graph Neural Network and thus it can handle large graphs more effectively than other approaches