Content adaptation and learner profile definition: Ant colony algorithm application

Abstract

E-Iearning is currently in expansion. Several studies were conducted to adapt courses according to learner's profile. In this article, we propose an e-Iearning adaptive system: Ant Colony Adaptive E-Learning (ACAEL). ACAEL is composed of three parts. The first part defines learner's profile using multi-criteria evaluation. We propose four criteria: active time spent consulting course units, evaluation time, number of attempts and finally the test score. Learner takes a global test and other tests corresponding to learning unit, during his elearning path. In the second part of ACAEL, using ant colony algorithm we define the succession of units and propose them to the learner. For each unit, the trainer assigns weights and a description of prerequisites and acquired information. We define units' succession and finally we obtain the personalized learner path. In the third part of ACEAL, we develop satisfaction survey component for learners and trainers, in order to improve course content and adaptive system.