Modeling Social Media Recommendation Impacts Using Academic Networks: A Graph Neural Network Approach

TL;DR

This work investigates how recommender systems shape social networks by using academic networks as a proxy for social media interactions. It introduces a Graph Neural Network framework that decouples Infosphere (recommender-exposed information) from user behavior, enabling simulation of recommender-generated infospheres and evaluation via future co-authorship link prediction. The methodology combines time-evolving heterogeneous graphs, seedgraph-based infosphere expansion, and encoder–decoder GNNs to assess how infospheres influence predictive performance. Experiments on the DBLP-Citation-network dataset show that incorporating an infosphere substantially improves prediction accuracy for new edges, with best gains when the seedgraph expansion is limited, providing insights into the potential effects of recommender systems on academic collaboration networks and broader social platforms.

Abstract

The widespread use of social media has highlighted potential negative impacts on society and individuals, largely driven by recommendation algorithms that shape user behavior and social dynamics. Understanding these algorithms is essential but challenging due to the complex, distributed nature of social media networks as well as limited access to real-world data. This study proposes to use academic social networks as a proxy for investigating recommendation systems in social media. By employing Graph Neural Networks (GNNs), we develop a model that separates the prediction of academic infosphere from behavior prediction, allowing us to simulate recommender-generated infospheres and assess the model's performance in predicting future co-authorships. Our approach aims to improve our understanding of recommendation systems' roles and social networks modeling. To support the reproducibility of our work we publicly make available our implementations: https://github.com/DimNeuroLab/academic_network_project