Using Multinets for Learner Modelling
Proceedings of the 2007 conference on Artificial Intelligence in Education: Building Technology Rich Learning Contexts That Work
| Hi-index | 0.00 |
Bayesian networks have been successfully used for student modeling in many systems. In this paper we address the problem of Bayesian network structure construction and more particularly that of arc orientation. We think that, in the case of cognitive task modeling, the traditional causal interpretation of arc orientation is not adequate. Instead, we use the information flow to provide a systematic a priori analysis of the conditional dependencies between variables. Finally, we explain why we think that different Bayesian networks should be taken into account and how this could be done.