Big Data Analytics for Mental Health Education: A New Framework for University-Level Evaluation under Linguistic Confidence Interval Neutrosophic Numbers

In the contemporary educational ecosystem, mental health has emerged as a pivotal aspect of holistic student development. The integration of big data analytics offers a transformative path for evaluating the effectiveness of mental health education at universities. This study proposes a comprehensive framework that merges data-driven tools with pedagogical strategies to assess key indicators of mental health support efficacy. Ten criteria—including accessibility, awareness, analytics integration, and data ethics—are used to evaluate a diverse set of intervention alternatives ranging from AI-based detection systems to immersive VR training. By applying a structured multi-criteria decision-making (MCDM) approach, this research identifies optimal strategies that ensure privacy, responsiveness, and personalized support. The findings not only guide administrators in refining their mental health initiatives but also contribute to academic research by introducing a scalable evaluation model that can adapt across institutional contexts. We use the Linguistic Confidence Interval Neutrosophic Numbers (LCINN) to overcome uncertainty and vague information. We use the EDAS method to rank the alternatives and select the best strategies.