Digital Personalization of Learning in Higher Education Institutions: Adaptive Systems, Intelligent Tutoring Systems and Generative Artificial Intelligence

Abstract

The article substantiates a comprehensive approach to the digital personalization of learning in higher education through the integration of adaptive learning systems, intelligent tutoring systems, and generative artificial intelligence. The relevance of the study is determined by the need to account for individual differences among students in prior preparation, pace of learning, patterns of learning activity, digital readiness, and the need for differentiated support amid the digital transformation of higher education. The purpose of the article is to substantiate an integrated model of digital learning personalization and to identify its pedagogical opportunities, advantages, limitations, and conditions for effective implementation. The study applies analysis, comparison, systematization and synthesis of scholarly sources, secondary statistical analysis of open international data, and content analysis of analytical materials from Eurostat, OECD and UNESCO. The findings show that digital personalization operates at content, pace, level, pathway and support levels and involves dynamic adjustment of learning content, task difficulty and sequencing, learning pace, and the nature of pedagogical support according to individual learner progress. Adaptive, intelligent-tutoring and generative-personalized models are systematized, and their integration into a combined adaptive-intelligent model is substantiated. Statistical analysis demonstrates substantial heterogeneity in young people's digital readiness: in 2025, 63.80% of people aged 16–24 in the European Union used generative artificial intelligence, whereas 39.30% used it for formal education. The effectiveness of digital personalization is shown to depend on pedagogically grounded design, students' digital readiness, teachers' competence, the quality and verifiability of generated content, academic integrity, personal data protection, technical interoperability of digital systems, and systematic evaluation of learning outcomes. The scientific novelty lies in refining the conceptualization of digital personalization as a multi-level pedagogical system and substantiating a combined model that integrates learning-path adaptation, intelligent diagnosis, personalized feedback and content generation while preserving the leading pedagogical role of the teacher.