User-Adaptive Visualizations: Can Gaze Data Tell Us When a User Needs Them?

Cristina Conati, Giuseppe Carenini, Mona Harati, Dereck Toker, Nicholas FitzGerald, Anna Flagg

Abstract: The primary goal of our research is to design adaptive information visualization systems that adapt to the specific needs of each individual viewer. Our first step is to explore data sources that could help detect these needs in real-time, including cognitive measures that impact perceptual abilities, interface interactions, eye-tracking, and physiological sensors. In this paper, we focus on current efforts to understand which cognitive measures can be relevant, as well as if/how a viewer's gaze pattern can predict performance on associated visualization task.