Abstract:

Education is potentially at the dawn of a new era: the capability to deliver learning on a more individualised basis. Data-driven methodologies enable personalised education and improve outcomes for students, educators and administrators.

The use of data is a crucial component in personalised learning, which ensures that student learning experiences—what they learn and how, when, and where they learn it—are tailored to their individual needs, skills, and interests and enable them to take ownership of their learning.

The objective of this article is to develop a model for creating and delivering personalised e-learning to provide lifelong learning that analyses the knowledge and skills accumulated by the learners and, on this basis, to provide them with a personalised learning path. In this way, the aim is to increase the efficiency of online learning by reducing the time for completion of the training and to increase the motivation of each individual participant.

In order to achieve the goal, the existing models for providing personalised e-learning are analysed, outlining their main disadvantages. The development of the model is based on the need to decompose the training content into small training objects to be parameterised with descriptive data at the stage of e-learning creation. For this purpose, a methodology has been chosen for describing decomposed knowledge with specific tags that are pooled under the general term "competences". To provide a Knowledge Validation Competence Database, open competences databases are analysed, including the specific knowledge, skills, abilities and tasks applicable to the widest possible range of professions.

As a result of the research and analyses, a model has been developed which, through an analysis complex based on case studies and questions, puts the learner in situations that have been previously described what competences and degree of reliability validate. Based on the decisions / responses / outcomes provided, each learner is assigned a competence profile. The developed model provides an effective comprehension of the actual learning content based on the learner's obtained competence profile, the pre-programmed logic of interrelation, and the degree of importance of the separate segments of the e-learning course.

Keywords:

Personalised education, learning management platforms, data-driven education.