Fairness and Polarization in Social Networks

The field of social network research is moving towards a stronger focus on fairness and polarization. Recent studies have highlighted the importance of ensuring equitable influence distribution across all communities, regardless of protected attributes. Researchers are also exploring the phenomenon of filter bubbles and their negative effects, such as group polarization. Moreover, the quantification of structural polarization in social and information networks has become a critical challenge. Noteworthy papers include: DQ4FairIM, which proposes a fairness-aware influence maximization method using deep reinforcement learning. DSP introduces a statistically-principled structural polarization measure that corrects for biases in existing measures.

Sources

DQ4FairIM: Fairness-aware Influence Maximization using Deep Reinforcement Learning

Identifying preferred routes of sharing information on social networks

Quantifying the Potential to Escape Filter Bubbles: A Behavior-Aware Measure via Contrastive Simulation

Community Quality and Influence Maximization: An Empirical Study

DSP: A Statistically-Principled Structural Polarization Measure

Exploring YouTube's Political Communication Networks during the 2024 French Elections

Built with on top of