ODALA, an Ontological Model for an Automated Evaluation of the Learner's State of Knowledge: Application to a Web-Based Algorithmic Teaching

10.6702/ijbi.2009.4.1.1

Farida Bouarab-Dahmani；Malik Si-Mohammed；Catherine Comparot；Pierre-Jean Charrel

Self-learning ； error diagnosis ； automated evaluation ； learner's marking ； learner model ； e-learning

International Journal of Business and Information

4卷1期（2009 / 06 / 01）

1 - 22

英文

This paper presents an approach for the automated evaluation of the learner's state of knowledge in an intelligent tutoring system, based on a granular and ontological model of the teaching domain. This approach, called ODALA (Ontology-Driven Auto-Evaluation for Learning Approach), is now being implemented in different self-learning settings, particularly those concerned with algorithmic teaching. ODALA represents the teaching domain as a domain ontology, which not only allows the evaluation to be propagated in each of the domain's components, but also facilitates error classification and detection. The evaluation process includes an error diagnosis module, a marking process, and an update of the learner model, all of which produce a well-calculated knowledge of the state of learners at different abstraction levels. This paper also presents results of the development and experimentation of our algorithmic self-learning system.