Probabilistic reasoning in intelligent systems: networks of plausible inference
Probabilistic reasoning in intelligent systems: networks of plausible inference
Assessing Effective Exploration in Open Learning Environments Using Bayesian Networks
ITS '02 Proceedings of the 6th International Conference on Intelligent Tutoring Systems
Modelling ubiquity for second language learning
International Journal of Mobile Learning and Organisation
User models for adaptive hypermedia and adaptive educational systems
The adaptive web
| Hi-index | 0.00 |
In this paper the underlying knowledge model and architecture of I-PETER (Intelligent Personalised English Tutoring EnviRonment) are presented. This system has been designed for the on-line distance learning of English where too many students restrict the teacher's possibilities to provide individualised guidance. I-PETER is made up of four domain models that represent linguistic and didactic knowledge: the conceptual framework related to linguistic levels and knowledge stages, and the educational content and study strategies. The student model represents the knowledge that the student has learnt, the study strategies, and his/her profile. A student's command of English is evaluated by interpreting his/her performance on specific linguistic units in terms of three related criteria, rather than by a general linguistic competence ranking. Evaluation consists of a diagnostic task model which assesses student performance, taking the form of a Bayesian network, and a selection mechanism that proposes appropriate materials and study strategies.