Toward User-Adaptive Visualizations

Cristina Conati
DFP Classroom: FSC 2300

User-adaptive interaction (UAI), a field at the intersection of artificial intelligence (AI) and human-computer interaction (HCI), aims to create AI-driven interactive systems that can personalize the interaction to their users by modelling and adapting in real-time to relevant users' needs, states and abilities. The benefits of UAI have been shown for a variety of tasks and applications. In this talk, I will describe our  research on applying concepts and methods from UAI to devising user-adaptive visualizations. I will present results on which user differences we found to  be relevant for personalizing  visualizations, and on  how these differences can be captured using predictive machine learning models based on eye-tracking data.