Learner Models: The Gap between Educational Opportunities vs. Data Protection Challenges

Abstract

Learners differ vastly in various aspects of what they need for successful learning. Artificial Intelligence (AI) provides a basis for digital learning environments that automatically adapt to learners' needs. To do so, these systems presuppose knowledge of the individual learner. Learner models are digital representations of learner characteristics that aim to enable personalised and adaptive learning experiences, addressing key areas such as transparency, fairness, data protection, modularity, and sustainability. Such learner models form the core of AI-based adaptive learning environments, as they store data about individual learners. This paper collects and discusses requirements, legal issues, and challenges associated with developing and using learner models, particularly in the context of European regulations. By reviewing existing standards, scientific publications, and practical use cases, we identify gaps in standardisation and propose foundational requirements for designing interoperable, legally compliant learner models. Our findings lay the groundwork for developing a reference architecture that facilitates the scalable and ethical integration of learner models in digital learning environments.

more

Mehr zum Titel

Titel Learner Models: The Gap between Educational Opportunities vs. Data Protection Challenges
Medien Int. Journal on Advances in Intelligent Systems
Herausgeber IARIA
Heft 1
Band 19
Verfasser Felix Böck, Hendrik Link, Prof. Dr. Dieter Landes
Veröffentlichungsdatum 2026-06-01
Projekttitel VoLL-KI
Zitation Böck, Felix; Link, Hendrik; Landes, Dieter (2026): Learner Models: The Gap between Educational Opportunities vs. Data Protection Challenges. Int. Journal on Advances in Intelligent Systems 19 (1).