© Springer International Publishing Switzerland 2015 C. Conati et al. (Eds.): AIED 2015, LNAI 9112, pp. 358–366, 2015. DOI: 10.1007/978-3-319-19773-9_36 Understanding Student Success in Chemistry Using Gaze Tracking and Pupillometry Joshua Peterson 1() , Zachary Pardos 1 , Martina Rau 2 , Anna Swigart 1 , Colin Gerber 1 , and Jonathan McKinsey 1 1 University of California, Berkeley, California {jpeterson,pardos}@berkeley.edu 2 Department of Educational Psychology, University of Wisconsin, Madison, Wisconsin marau@wisc.edu Abstract. Eye tracking allows us to identify visual strategies through gaze beha- vior, which can help us understand how students process content. Furthermore, understanding which visual strategies are successful can help us improve educa- tional materials that foster successful use of these visual strategies. Previous studies have demonstrated the predictive value of eye tracking for student perfor- mance. Chemistry is a highly visual domain, making it particularly appropriate to study visual strategies. Eye tracking also provides measures of pupil dilation that correlate with cognitive processes important to learning, but have not yet been as- sessed in any realistic learning environments. We examined the gaze behavior and pupil dilation of undergraduate students working with a specialized ITS for che- mistry: Chem Tutor. Chem Tutor emphasizes visual learning by focusing specifi- cally on graphical representations. We assessed the value of over 40 high-level gaze features along with measures of pupil diameter to predict student perfor- mance and learning gains across an entire chemistry problem set. We found that certain gaze features are strong predictors of performance, but less so of learning gains, while pupil diameter is marginally predictive of learning gains, but not per- formance. Further studies that assess pupil dilation with higher temporal precision will be necessary to draw conclusions about the limits of its predictive power. Keywords: Eye tracking · Intelligent tutoring systems · Performance prediction · Chem tutor 1 Introduction Eye tracking provides behavioral and physiological metrics that researchers can use to study a number of psychological and physiological processes. In the context of educa- tion, these metrics can reveal visual strategies and provide clues as to how students process content. Armed with such knowledge, instructional designers can build better content and interfaces for Massive Open Online Courses (MOOCs), Intelligent Tutor- ing Systems (ITS), and with the advent of affordable and wireless head-mounted trackers, perhaps even traditional classrooms. While eye tracking research applied to education has already begun to yield insights into students’ behavior and internal