Digital Transformation in Higher Education Through Interactive Ontology and Multiobjective Optimization for Evidence-Based Strategic Prioritization

Digital transformation in higher education has increasingly shifted from a technology-centered agenda toward a multidimensional institutional process involving governance, quality assurance, process redesign, and data-driven decision-making. This study proposes and operationalizes an analytical framework for examining digital transformation in universities through an interactive Human–Machine Interface developed in Python. The framework is structured around three complementary methodological cores: ontology-based modeling, statistical reliability analysis, and multiobjective optimization. The ontology module organizes the semantic structure of digital transformation dimensions, revealing their relational hierarchy and structural relevance. The statistical module evaluates internal consistency and distributional behavior through Cronbach’s alpha, corrected item–total correlation, and density-based inspection. The optimization module formulates intervention selection as a constrained multiobjective problem, allowing the identification of efficient portfolios under cost, readiness gain, equity, and feasibility criteria. The analytical environment also incorporates interactive dashboards, VOSviewer-style relational exploration, and exportable high-resolution figures. Results show that digital transformation readiness is heterogeneous across groups, that governance-oriented dimensions occupy a central semantic role, and that institutional intervention planning benefits from Pareto-efficient decision support rather than single-criterion ranking. The study contributes a coherent bridge between conceptual models of digital transformation and an operational analytical environment capable of supporting institutional diagnosis, evidence-based prioritization, and strategic planning in regulated higher education settings.