Adjustable Learning Style Recognition based on 3Layers Fuzzy Cognitive Map

The learner’s Learning Style (LS) recognition has been proved a cornerstone to Adaptive Educational Hypermedia Systems’ (AEHS) design. Like some of the other well known cognitive (and affective) taxonomies, the Kolb taxonomy illustrates a range of interrelated learning abilities and styles beneficial to novices and experts. As AEHSs designed to emphasize reflection on learners’ experiences, progressive conceptualization and active experimentation, it is expected that this kind of environment is congruent with the aim of asynchronous e-learning. In AEHS the user’s LS recognition becomes one of the basic components. The research question this paper attempts to answer deals with the ability of an AEHS to allow human’s interference for LS recognition improvement. Using Learning Ability Factors we propose a model that allows tutors to refine the functionality of a LS recognition schema that is based on a three layer’s Fuzzy Cognitive Maps. Using the Kolb’s LS Inventory, the proposed system allows the tuning of the system’s parameters to the purpose of adjusting the accuracy of the LS recognition. To conclude this research, the proposed model is implemented on a test group of 102 university’s students and the results justified the system’s adjustability.