A Framework for Improving Social Inclusion Using Network Analysis and IoT-Based Contact Tracing

Social isolation poses critical challenges, with profound implications for performance, mental health, and general well-being. We present a framework to quantitatively measure social inclusion and suggest actions to increase the integration of isolated individuals. Specifically, we address the problem of detection and mitigation of social isolation in educational contexts-a pressing concern where the fundamental role of peer relationships contributes to determining student health and academic success. To tackle this challenge, we employ affordable, off-the-shelf IoT devices for reliably detecting face-to-face social interactions. On the detected network, we employ network analysis techniques, particularly PageRank and Betweenness centrality, to propose a novel algorithm that infers social inclusion levels and recommends sustainable interventions aligned with natural interaction patterns, thus ensuring sustainable integration. Our approach addresses the growing need for evidence-based, scalable solutions implementable across diverse educational environments without substantial infrastructure investment. We validate the framework through a real-world case study in a primary school, demonstrating the effectiveness of our methods in identifying socially isolated students and providing actionable insights for their social integration, offering an affordable tool for addressing one of education's most persistent challenges.