A graph-based recommender system for training groups in the professional context
Laurie Acensio, Université Lille 1UMR CNRS 9189 CRISTAL, France ; Frédéric Hoogstoel, Polytech'Lille-Université de Lille, Lille, France, France ; Luigi Lancieri, Université de Lille-Equipe NOCE, Laboratoire d’Informatique Fondamentale de Lille (LIFL), France
EdMedia + Innovate Learning, in Amsterdam, Netherlands Publisher: Association for the Advancement of Computing in Education (AACE), Waynesville, NC
In the context of vocational training, the composition of the optimal training group must take into account the socio-professional aspects of the learners' profiles. Indeed, the training group is subject to structural characteristics specific to the field of application that can influence potential collaborations during a face-to-face training session (composition, size, duration). This research work aims to present our modelling methodology from a perspective of a recommender system to assist in the composition of training groups. Our approach consists in aggregating learners' individual preferences by incorporating the concepts of social network theory, in particular by polarizing the nature of inter-professional relations.
Acensio, L., Hoogstoel, F. & Lancieri, L. (2018). A graph-based recommender system for training groups in the professional context. In T. Bastiaens, J. Van Braak, M. Brown, L. Cantoni, M. Castro, R. Christensen, G. Davidson-Shivers, K. DePryck, M. Ebner, M. Fominykh, C. Fulford, S. Hatzipanagos, G. Knezek, K. Kreijns, G. Marks, E. Sointu, E. Korsgaard Sorensen, J. Viteli, J. Voogt, P. Weber, E. Weippl & O. Zawacki-Richter (Eds.), Proceedings of EdMedia: World Conference on Educational Media and Technology (pp. 58-62). Amsterdam, Netherlands: Association for the Advancement of Computing in Education (AACE).
© 2018 Association for the Advancement of Computing in Education (AACE)