Abstract: | In this paper we argue that there are benefits to extending the scope of student models to include additional information as part of the explicit student model, for example a system should not only take account of a learner's performance in the domain, but also his beliefs. Issues such as the sequencing of material can be important in some subjects. The possibility of (positive and negative) analogy should also be considered, as should a learner's general approach to learning. As an illustration we describe the student model of an intelligent computer assisted language learning (ICALL) system which focuses on 1. performance in the domain; 2. acquisition order of the target rules; 3. language transfer; 4. learning strategies; 5. language awareness. The system has been based on research findings in the field of second language acquisition (SLA). The student model has been designed to model real errors (identified from a corpus of students' work), and also learning-related issues. The student model is also used to promote learning reflection by encouraging the learner to view, discuss and even suggest changes to the model.
|