TY - JOUR AU - Ting, Choo-Yee AU - Phon-Amnuaisuk, Somnuk PY - 2009 TI - Log data Approach to Acquisition of Optimal Bayesian Learner Model JF - American Journal of Applied Sciences VL - 6 IS - 5 DO - 10.3844/ajassp.2009.913.921 UR - https://thescipub.com/abstract/ajassp.2009.913.921 AB - 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