Using a hybrid AI approach for exercise difficulty level adaptation

Abstract

An intelligent and adaptive web-based education system is presented. The system uses a hybrid AI approach, a combination of an expert systems approach and a genetic algorithm approach, to determine the difficulty levels of the provided exercises. The genetic algorithm is used to extract some kind of rules from the data acquired from the interactions of the students. Those rules are used to modify expert rules provided by the Tutor. In this way, feedback from the students is taken into account for determination of the difficulty levels of the questions/exercises. Experimental results show the validity of the method.