Bayesian student modeling and the problem of parameter specification

@article{Milln2001BayesianSM,
title={Bayesian student modeling and the problem of parameter specification},
author={Eva Mill{\'a}n and J. M. Agosta and Jos{\'e}-Luis P{\'e}rez-de-la-Cruz},
journal={BJET},
year={2001},
volume={32},
pages={171-181}
}

In this paper, the application of Bayesian networks to student modeling is discussed. A review of related work is made, and then the structural model is defined. Two of the most commonly cited reasons for not using Bayesian networks in student modeling are the computational complexity of the algorithms and the difficulty of the knowledge acquisition process. We propose an approach to simplify knowledge acquisition. Our approach applies causal independence to factor the conditional probabilities… CONTINUE READING