Inferring learning and attitudes from a Bayesian Network of log file data

摘要: A student's goals and attitudes while interacting with a tutor are typically unseen unknowable. However their outward behavior (e.g. problem-solving time, mistakes help requests) is easily recorded can reflect hidden affect status. This research evaluates the accuracy of Bayesian Network to infer attitude toward learning, amount learned perception system from log-data. The long term goal develop tutors that self-improve student models teaching, dynamically adapt pedagogical decisions about hints improve affective, intellectual learning situation based on inferences attitude.