Abstract
Learning online (e-learning) has gained popularity in a world where emerging technologies are transforming the world in particular self-training due to what it provides of low-cost learning and relieving the learner of all logistical concerns that traditional learning methods impose. Although e-learning systems have managed to establish many advantages, in terms of time management, and economic level, and also provide much more learning freedom when it comes to when and where a person wants to learn. Some improvements in the learning sessions themselves are needed. Mentioning adaptability between user profiles, the variable personal user preferences during his/her learning sessions, and the learning path. In this work, and to address that issue we propose a system that recommends learning graphs to users based on their profiles, preferences, and progress, based on an analytic review of experiences from multiple users' learning sessions. Having three ontologies: User Profile Ontology to model the learner, Training Ontology, and MultiMedia Resources Ontology modeling respectively the domain and resources. We analyze the users' session history stored in those ontologies to produce recommendations based on matching profiles, taking advantage of the web semantic multiple uses.
Author Information
Massra Sabeima, University of Paris 8, France
Myriam lamolle, University of Paris 8, France
Mohamedade Farouk Nanne, University of Nouakchott, Mauritania
Paper Information
Conference: PCE2023
Stream: Adult
This paper is part of the PCE2023 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window
To cite this article:
Sabeima M., lamolle M., & Nanne M. (2023) Analytic Recommendation of Learning Graphs Based on User’s Learning History ISSN: 2758-0962 The Paris Conference on Education 2023: Official Conference Proceedings https://doi.org/10.22492/issn.2758-0962.2023.65
To link to this article: https://doi.org/10.22492/issn.2758-0962.2023.65
Comments
Powered by WP LinkPress