A cognitive theory for affective user modelling in a virtual reality educational game

The educational community in general considers computer-assisted learning to be very beneficial. As a result, numerous new educational software applications are being developed. An educational application can become very effective if it is adaptive and individualised to the student. However, one important aspect of students that has been overlooked so far, and should be included in such individualisation models, is students´ behaviour and emotional state that affects their learning. This paper describes how system observations of students´ behavioural characteristics, during their interaction with an educational application, may provide important evidence about students´ emotions while they learn. The information collected from these observations mainly concerns students´ behaviour while using the application, combined with students´ reactions and responds to questions depending on the correctness of their answers. The system´s inferences about students´ emotions are used to adapt interaction to each individual student´s needs taking into account their character and mood.