A fuzzy linguistic algorithm for adaptive test in Intelligent Tutoring System based on competences

The Computerized Adaptive Tests (CAT) are common tools for the diagnosis process in Intelligent Tutor System based on Competency education (ITS-C). The item selection process to form a CAT plays a key role because it must ensure the selection of the item that best contributes to student assessment at any time. The item selection mechanisms proposed in the literature present some limitations that decrease the efficiency of CAT and its adaptation to the student profile. This paper introduces a new item selection algorithm, based on a multi-criteria decision model that integrates experts’ knowledge modeled by fuzzy linguistic information that overcomes previous limitations and enhances the accuracy of diagnosis and the adaptation of CAT to student’s competence level. Finally, such an algorithm is deployed in a mobile tool for an ITS-C.