Towards a Trace-Based Adaptation Model in eLearning Systems

Abstract

Adaptive learning systems aim to personalize and adapt resources and learning strategies according to learners' knowledge acquisition and behavior. In this paper, knowledge acquisition is estimated by using traces learners left during their learning activities. Learner's traces considered are activity duration and number of attempts to solve a given problem, upon which we developed a trace-based evaluation model. The latter is integrated into a trace-based adaptation model made of ontological rules and reasoning mechanism to deliver adapted resources and personalized learning strategy, represented as learning paths, which are sequences of situations containing resources. The reasoning mechanism is implemented as a state-transition process governed by an adaptation algorithm we proposed.