Assessment personalization in the Semantic Web

The work described in this paper relates to the formal description, implementation and use of a web-based personalized assessment system. The assessment techniques are formalized with First Order Logic rules which are able to reason over resources annotated with Semantic Web metadata formats according to LOM and IMS/QTI standards. They were tested using TRIPLE, a rule-based language for the Semantic Web. We also describe the service-based architecture, which was implemented as part of the Personal Reader Framework. Personalization functionalities are available as web services that communicate via Semantic Web technologies without the need for centralized control. Appropriate assessment resources are searched after checking the learner's last saved performance. We illustrate this system with an object oriented programming course taken by students in our university.