Application of machine learning to the learning analytics of the Moodle platform to create heterogeneous groups in on-line courses

  • Giacomo Nalli School of Science and Technology, University of Camerino, Italy
  • Leonardo Mostarda School of Science and Technology, University of Camerino, Italy
  • Andrea Perali School of Pharmacy, University of Camerino, Italy
  • Sebastiano Pilati School of Science and Technology, University of Camerino, Italy
  • Daniela Amendola School of Bioscences and Veterinary Medicine, University of Camerino, Italy

Abstract

In university courses to promote collaborative activities among students, on-line learning
environments such as e-learning platforms are used. Effective collaborative activities
involve the creation of heterogeneous groups of 4 or 5 students. In the university context
the formation of groups is difficult due to the high number of students. Groups are often
unbalanced and not very functional if chosen randomly. Some e-learning platforms, such
as Moodle, lack an intelligent mechanism that allows the automatic creation of heterogeneous
groups of students. We applied clustering algorithms on Moodle learning analytics
(LA) that allowed to build groupings that identify the different characteristics of
students based on their behaviors kept on the platform. Therefore we have developed
an intelligent numerical tool which, using clusters obtained from Machine Learning on
the LA, generates heterogeneous groups. These groups are made available on the platform
for the teacher. The project will conclude with the development of a Moodle plugin
to automate the exchange of data and information between the Machine Learning algorithm
and the Moodle platform.

Published
2019-10-16