EVENT-DRIVEN SIMILARITY AND CLASSIFICATION OF

ii Eye tracking experiments often involve recording the pattern of deployment of visual attention over the stimulus as viewers perform a given task (e.g., visual search). It is useful in training applications, for example, to make available an expert’s sequence of eye movements, or scanpath, to novices for their inspection and subsequent learning. It may also be potentially useful to be able to assess the conformance of the novice’s scanpath to that of the expert. A computational tool is proposed that provides a framework for performing such classification, based on the use of a probabilistic machine learning algorithm. The approach was influenced by the need to compute similarity of eye fixations at single points in time, such as would be required for video stimuli. This method is also useful for eye move-ment analysis over static images and some interactive tasks. The algorithm employs a common qualitative comparison method, the heatmap, in a quantitative way to measure deviation from group aggregate behavior. This quantitative comparison is performed at individual events, defined by the stimulus, such as frame timestamps of video or mouseclicks of interactive tasks. The algorithm is evaluated and found to be more accurate and discriminative than existing comparison algorithms for the stimuli used in the examined experiments. ii