"Comprehensive User Modeling for Intelligent User Interfaces"

02/25/05: 10:30 AM
10th Floor Conference Room
Host: Patrick Pantel, schedule

Abstract: Research in user modeling aims at giving interactive systems the capability of generating highly individualized interactions by creating real-time models of relevant user's traits. Most existing user models foduc on assessing a user's cognitive traits, such as knowledge, goals, beliefs, and preferences. In this talk, I will present our work on extending the range of features captured in a user model to include domain independent meta-cognitive skills and affective states. I will illustrate how we are applying this research to design innovative learning environments for open ended, student-led pedagogical interactions, focusing on our solutions to two major challenges in this research: how to increade model bandwidth to reduce the uncertainty in the modeling task; and how to devise sound techniques to validate the models.

About Cristina Conati: Dr. Conati is an Assistant Professor of Computer Science at the University of British Columbia. She received her Laurea degree (M.Sc. equivalent) in Computer Science at the University of Milan, and her M.Sc. and Ph.D. in Artificial Intelligence at the University of Pittsburgh. Dr. Conati's goal is to integrate research on Artificial Intelligence, Cognitive Science and Human Computer Interaction to make complex interative systems increasingly more effective and adaptive to the users' needs. Her areas of interest include Adaptive Interfaces, Intelligent Learning Environments, Probabilistic User Modeling, and Affective Computing. Dr. Conati has served on program committees and as a reviewer for major AI and HCI conferences/journals. Her research has received awards from the International Conference on User Modeling, the International Conference of AI in Education and in the Journal of User Modeling and User Adapted Interaction.

Last updated: Mon Jun 19 17:44:06 2006