Eye-tracking to model and adapt to user meta-cognition in intelligent learning environments

In this paper we describe research on using eye-tracking data for on-line assessment of user meta-cognitive behavior during the interaction with an intelligent learning environment. We describe the probabilistic user model that processes this information, and its formal evaluation. We show that adding eye-tracker information significantly improves the model accuracy on assessing user exploration and self-explanation behaviors. Categories and Subject Descriptors I.2.1 [Artificial Intelligence]: Applications and Expert Systems I.2.3 [Artificial Intelligence]: Deduction and Theorem Proving – uncertainty and probabilistic reasoning; K.3.1 [Computers and Education]: Computer Uses in Education – computer-managed instruction (CMI). General Terms Human Factors, Experimentation. Keywords Intelligent assistance for complex tasks, adaptive interfaces, user modeling, eye-tracking, meta-cognitive skills, intelligent learning environments

• Type: Conference
• Year: 2006
• Where: IUI
• Authors: Christina Merten, Cristina Conati
• Keywords: Intelligent Learning Environments, IUI 2006, Probabilistic User Model, Software Engineering, User