Modelling Learning in an Educational Game

We describe research on data-drive refinement and evaluation of a probabilistic model of student learning for an educational game on number factorization. The model is to be used by an intelligent pedagogical agent to improve student learning during game play. An initial version of the model was designed based on teachers’ advice and subjective parameter settings. Here we illustrate data-driven improvements to the model, and we report results on its accuracy.

• Type: Conference
• Year: 2005
• Where: AIED
• Authors: Micheline Manske, Cristina Conati
• Keywords: AIED 2005, Artificial Intelligence, Intelligent Pedagogical Agent, Probabilistic Model, Subjective Parameter Settings