Learning Faults Detection by AIS Techniques in CSCL Environments

By the increase of e-learning platforms, huge data sets are made from different kinds of the collected traces. These traces differ from one learner to another according to their characteristics (learning styles, preferences, performed actions, etc.). Learners’ traces are very heterogeneous and voluminous, so their treatments and exploitations are difficult, that make hard the tutors’ tasks. This paper introduces one of the bio-inspired computing techniques to improve the learning quality. In fact, Artificial Immune System (AIS) is a technique which was adapted for designing an assistant system that detects the wrong scenarios made by learners. Furthermore, this assistant system assists the learners in their activities. The main aim is to present the basic concepts of a new approach that aims at providing learners with relevant traces to improve their learning in order to minimize the tutor’s tasks. A novel algorithm is proposed to design the assistant system based on the two mechanisms of the AIS techniques (negative and clonal selection). The proposed algorithm was applied on a collaborative learning system called LETline 2.0 (http://www.labstic.com/letline/). An experiment was conducted in an Algerian University. The obtained results from this experiment were good and very efficient. The proposed approach enhances the cognitive and behavioral profiles of learners. In fact, the results show that the cognitive profiles of most students were improved. Also, it minimizes the tutor’s tasks.