About Me
I am a postdoctoral researcher at the School of Information, The University of Texas at Austin, working with Dr. Jacek Gwizdka. My research asks a simple question: what is happening in the mind while someone searches for information, reads a document, or decides whether to trust what they see? I use eye tracking and pupillometry to answer it in real time.
The eyes are remarkably honest. Where we look, how long we linger, and how our pupils respond to mental demand all carry traces of cognitive state that people cannot easily mask or report. I develop algorithms that read those traces live, while the interaction is still happening. My core contribution is gaze-based methods that track cognitive load as it rises and falls, capturing the difference between a task that fits comfortably within someone's mental capacity and one that pushes them to their limits. [1]Jayawardena, Jayawardana, and Gwizdka. "Measuring Mental Effort in Real Time Using Pupillometry." Journal of Eye Movement Research 18(6), 2025.
I apply these methods to questions that arise when people find and evaluate information and interact with AI. I have studied how prior beliefs distort the mental effort people invest in assessing document credibility, [2]Shi, Jayawardena, and Gwizdka. "Pupillometric Analysis of Cognitive Load in Relation to Relevance and Confirmation Bias." CHIIR 2025. how individual differences in working memory shape the cognitive cost of search, [3]Jayawardena, Shi, and Gwizdka. "Effects of Working Memory Capacity and Search Task Complexity on Cognitive Load." CHIIR 2026. and how visual attention shifts between broad scanning and deep reading as people move through a task. [4]Jayawardena et al. "A Real-Time Approach to Capture Ambient and Focal Attention in Visual Search." ETRA 2025. More recently, I have been examining what happens cognitively when people encounter AI-generated misinformation [5]Abeysinghe, Jayawardena, Kasneci, and Jayarathna. "Susceptibility to High-Fidelity Misinformation: An Eye-Tracking Analysis." ETRA 2026. and when they learn new concepts using AI. Gaze reveals a great deal about how the mind is engaging that people themselves are unaware of.
My earlier work showed that eye movement signals can predict an ADHD diagnosis with high accuracy, [6]Jayawardena, Michalek, Duchowski, and Jayarathna. "Predicting ADHD Using Eye Gaze Metrics Indexing Working Memory Capacity." Computational Models for Biomedical Reasoning, 2019. and that gaze patterns differ meaningfully between neurotypical and ADHD individuals across tasks like speech-in-noise [7]Jayawardena, Michalek, Duchowski, and Jayarathna. "Pilot Study of Audiovisual Speech-In-Noise (SIN) Performance of Young Adults with ADHD." ETRA 2020. and working memory. The pattern was clear: physiological gaze data carries information about how a mind works that no questionnaire or self-report can surface. That insight shapes everything I build.
My work has been recognized with the Lee Entsminger Outstanding Dissertation Award (2024-2025), the Best Doctoral Symposium Presentation Award at ETRA 2022, Best Paper and Best Poster awards at multiple venues, and graduate scholarships including the Dominion Graduate Scholar award and the Irwin B. Levinstein Scholarship.
I hold a Ph.D. in Computer Science from Old Dominion University (2024) and a B.Sc. in Computer Science and Engineering (First Class Honors) from the University of Moratuwa, Sri Lanka.