2013 | OriginalPaper | Buchkapitel
Using Educational Domain Models for Automatic Item Generation Beyond Factual Knowledge Assessment
verfasst von : Muriel Foulonneau, Eric Ras
Erschienen in: Scaling up Learning for Sustained Impact
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
The Semantic Web offers many opportunities for reusing datasets and domain models in the field of education and assessment in particular. We have conducted research to generate test questions from Semantic resources. The reuse of semantic resources raises however challenges, since all data and models have not been conceived to be directly used for educational purposes. We have therefore analysed existing domain models created specifically for educational contexts to identify structures and relations of the model that can help deem the relevance of a particular domain model for automatic item generation. We present an initial set of conditions which can help identifying a relevant domain model to be used in an educational context. We also suggest a mechanism to relate them to levels of knowledge to be assessed in generated items.