Temporal social network modeling of mobile connectivity data with graph neural networks

2025-09-03

AI Summary

This study investigates the predictive capability of graph neural networks (GNNs) for dynamic user interaction patterns in temporal social networks derived from mobile communication data (calls/SMS). We propose ROLAND, a GNN architecture specifically designed for snapshot-based temporal graphs, and conduct systematic empirical evaluation on real-world mobile social datasets. Experimental comparisons against four snapshot-based temporal GNN baselines and a non-GNN edge-level predictor (EdgeBank) demonstrate that ROLAND consistently outperforms all baselines across most metrics—validating the efficacy of temporal GNNs for this task—yet reveals only marginal performance gains, highlighting inherent limitations of generic architectures in modeling social interaction semantics. Our contributions are threefold: (1) establishing a benchmark for temporal graph modeling tailored to mobile social scenarios; (2) proposing and empirically validating ROLAND’s effectiveness; and (3) underscoring the necessity of social-semantics-aware, domain-specific temporal GNN designs.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Planning, Routing, and Scheduling: Temporal Planning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Social Networks and Social Media: Social mining and social search on the Web
• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web

Abstract

Graph neural networks (GNNs) have emerged as a state-of-the-art data-driven tool for modeling connectivity data of graph-structured complex networks and integrating information of their nodes and edges in space and time. However, as of yet, the analysis of social networks using the time series of people's mobile connectivity data has not been extensively investigated. In the present study, we investigate four snapshot - based temporal GNNs in predicting the phone call and SMS activity between users of a mobile communication network. In addition, we develop a simple non - GNN baseline model using recently proposed EdgeBank method. Our analysis shows that the ROLAND temporal GNN outperforms the baseline model in most cases, whereas the other three GNNs perform on average worse than the baseline. The results show that GNN based approaches hold promise in the analysis of temporal social networks through mobile connectivity data. However, due to the relatively small performance margin between ROLAND and the baseline model, further research is required on specialized GNN architectures for temporal social network analysis.

Problem

• Modeling temporal social networks with mobile connectivity data
• Evaluating GNN performance against non-GNN baseline methods
• Predicting phone call and SMS activity between users

Innovation

• Using graph neural networks for temporal analysis
• Developing EdgeBank baseline for mobile connectivity
• Evaluating ROLAND model outperforming other methods