On Scaffolding Adaptive Teaching Prompts Within Virtual Labs

Abstract

Despite a growing development of virtual laboratories which use the advantages of multimedia and Internet for distance education, learning by means of such tutorial tools would be more effective if they were specifically tailored to each student needs. The virtual teaching process would be well adapted if an artificial tutor can identify the correct acquired knowledge, recognise the erroneous learner’s knowledge and suggest a suitable sequence of pedagogical activities to improve the level of the student. This paper proposes a knowledge representation model which judiciously serves the remediation process to students’ errors during e-learning activities. The model is inspired by recent researches on computational representation of the knowledge and by cognitive psychology theories that offer a refined modelling of the human learning processes. Experimental results, obtained via practical tests, show that the knowledge representation and remediation approach facilitates the planning of tailored sequences of feedbacks that considerably help the learner.