E-Learning: An Assessment Tool Based on a Bayesian Approach

Assessment of student learning is an important task in teaching and learning process. It has a strong influence on students' approaches to learning and their outcomes. But what is assessment? Assessment, in the context of education, is the process of characterizing what a student knows. The reasons to perform evaluation are quite varied, ranging from a need to informally understand student learning progress in a course to a need to characterize student expertise in a subject. Finding an appropriate and effective assessment approach is a central challenge in designing a tutoring approach. However, it sometimes happens that the assessment criteria and their corresponding weights are solely determined by the lecturers in charge and on the other hand an effective assessment program is extremely difficult to maintain as class sizes increase. The aim of this paper is the introduction of a tutoring approach based on the assessment results. This strategy is mainly developed for the supporting of the e-Learning formative process. The starting point of the proposed approach is the representation of the course knowledge domain by the use of the ontology formalism. In this way, by an original mapping strategy between ontology and Bayesian Network, we can design a tool for the generation of adapted questionnaires in order to test the student's knwoledge of every domain's subject. Analyzing the obtained results of the evaluation an intelligent tutoring system can help students offering an effective support to learning process and adapting their learning path