American Journal of Applied Sciences

Log data Approach to Acquisition of Optimal Bayesian Learner Model

Choo-Yee Ting and Somnuk Phon-Amnuaisuk

DOI : 10.3844/ajassp.2009.913.921

American Journal of Applied Sciences

Volume 6, Issue 5

Pages 913-921


Log data provide valuable insight into observable behavioural patterns, which could be inferred to study a learner’s cognitive processes, levels of motivation and levels of knowledge acquisition. To date, most of the research work has been devoted to study the different methods to analyze and interpret log data. Little attention, however, has been given to use log data as a tool to investigate the behaviour of Bayesian learner models. In this light, this article discusses how log data could be employed to investigate the performance of Bayesian learner models. The log data were firstly transformed into a set of structured dataset, which conformed to the INQPRO’s learner model. The transformed dataset were then fed into different versions of INQPRO’s learner model to obtain their predictive accuracies. From the predictive accuracies, an optimal learner model was identified. Empirical results indicated that the log data approach provides an efficient way to study the behaviour of a Bayesian learner model


© 2009 Choo-Yee Ting and Somnuk Phon-Amnuaisuk. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.