Dynamic Group Formation based on a Natural Phenomenon

Abstract

This paper presents a new approach of learners grouping in collaborative learning systems. This grouping process is based on traces left by learners. The goal is the circular dynamic grouping to achieve collaborative projects. The proposed approach consists of two main algorithms: 1 the circular grouping algorithm and 2 the dynamic grouping algorithm used to update groups. The circular grouping is a novel algorithm to group learners based on their learning and collaborative traces. So, the aim is to form heterogeneous groups based on their profiles. The dynamic grouping algorithm is based on the behavior of penguins when they are moving in the winter season to secure their lives. The new proposed approach used the same behavior of penguins' colony. The proposed approach was applied on a collaborative learning system called LETline 2.0 http://www.labstic.com/letline/. The developed system was experimented at an Algerian university. After the experiment, the authors observed that their system groups automatically the learners into homogeneous groups and improves their cognitive profiles.