A Diversity-Enhanced Genetic Algorithm to Characterize the Questions of a Competitive e-Learning System

Nowadays, the practice of different teaching methodologies is easier thanks to the technology-enhanced learning systems. However, in order to effectively center the learning process in the student it should be adapted to the student’s progress. Adaptive e-learning systems have been proved to be valuable tools, which facilitate this adaptation. QUESTOURnament, an active and competitive Moodle tool, is being re-designed in order to become an adaptive system. One of the first steps in this adaptation is the estimation of the difficulty level of the questions proposed in this environment. This paper describes a solution based on a genetic algorithm with enhanced diversity methods that automatically characterizes the answers to the challenges. The algorithm has been tested with data registered from a contest made in a Telecommunications Engineering course. It finds diverse good solutions, from which several rules can be defined to classify the questions according to their difficulty level.