Mr. Collins: A collaboratively constructed, inspectable student model for intelligent computer assisted language learning

Abstract

This paper describes ‘Mr. Collins’, a student model for intelligent computer assisted language learning (ICALL), which is based on the results of empirical studies conducted in the target domain. ‘Mr.Collins’ is constructed and updated through student/system collaboration. This collaborative approach to learner modelling aims both to promote student reflection through discussion of the student-model, and to provide more detailed and accurate information for the model. Due to his own contributions the student is less likely to regard the model with suspicion. Because the student model is the focus of the system, it must contain more information than is typically found in learner models. Therefore, in addition to domain knowledge and misconceptions, ‘Mr. Collins’ also models learner confidence, background languages and learning strategies. The typical acquisition sequence for the target rules is explicitly modelled to provide an additional perspective from which the system may assess learner input.