Enhancing Personalized Learning Through Process Mining

Abstract Technology-mediated learning offers new possibilities for individualizing learning processes in order to discover, monitor, and enhance students’ learning activities. However, leveraging such possibilities automatically and at scale with novel technologies raises questions about the design and the analysis of digital learning processes. Process mining hereby becomes a relevant tool to leverage these theorized opportunities. The paper classifies recent literature on individualizing technology-mediated learning and educational process mining into four major concepts (purpose, user, data, and analysis). By clustering and empirically evaluating the use of learner data in expert interviews, the study presents three design patterns for discovering, monitoring, and enhancing students’ learning activities by means of process mining. The paper explains the characteristics of these patterns, analyzes opportunities for digital learning processes, and illustrates the potential value the patterns can create for relevant educational stakeholders. Information systems researchers can use the taxonomy to develop theoretical models to study the effectiveness of process mining and thus enhance the individualization of learning processes. The patterns, in combination with the taxonomy for designing and analyzing digital learning processes, serve as a personal guide to studying, designing, and evaluating the individualization of digital learning at scale.