PLM – An Open Learner Model for Adaptive Learning Environments - Specification

Abstract

The growing need for individualised support in digital learning environments leads to the development of adaptive learning systems based on so-called learner models. These models represent a learner's digital information and enable personalised recommendations and learning paths tailored to their needs, prior knowledge and preferences. This paper's central research question deals with how a learner model must be designed to be used effectively in adaptive learning environments and recommendation systems. Based on a comprehensive analysis of existing models and legal restrictions, a learning model was developed that is based on European legal principles and will be open source in the future to make it easier for other educational institutions in Europe to get started. This is being tested iteratively in the form of a prototype as a step toward a comprehensive and generalised open learning model. The developed Pentagonal Learner Model (PLM) is characterised by two dimensions: The allocation of data to specialist areas and the frequency with which it is updated. The model enables a differentiated view of learning and behavioural data, which is required for personalised learning paths, as well as additional analysis of knowledge data about the learner. However, a significant challenge remains in handling data protection and balancing the need for detailed learning data and privacy protection. Future work must investigate what data is necessary for successful utilisation and how learner acceptance can be ensured.

Mehr zum Titel

Titel PLM – An Open Learner Model for Adaptive Learning Environments - Specification
Medien Proc. IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE 2025)
Verfasser Felix Böck, Prof. Dr. Dieter Landes
Veröffentlichungsdatum 2025-12-04
Projekttitel VoLL-KI
Zitation Böck, Felix; Landes, Dieter (2025): PLM – An Open Learner Model for Adaptive Learning Environments - Specification. Proc. IEEE International Conference on Teaching, Assessment and Learning for Engineering (TALE 2025).