Open Collections

Abstract

The accuracy of a user model typically depends on the amount and quality of information available on the user's states on interest. An eye-tracker provides data indicating where a user is looking during interaction with the system. In this thesis we present research on the use of eye-tracking data for on-line assessment of user meta-cognitive behavior during the interaction with an open learning environment. We describe the design of a probabilistic model that processes this information and its formal evaluation. We demonstrate that adding eye-tracking information significantly improves the model accuracy on assessing user exploration and self-explanation behaviors.