Exploring Eye Tracking to Increase Bandwidth in User Modeling

by Christina Merten

The accuracy of a user model usually depends on the amount and quality of information available on the user's states of interest. An eye-tracker provides data detailing where a user is looking during interaction with the system. In this talk I will discuss findings from a user study that explores the usage of users' gaze patterns to understand whether students engage in a meta-cognitive behavior known as self-explanation, during interaction with an Intelligent Learning Environment for mathematical functions.

Back to the LCI Forum page