Abstract
Existing research has shown that human eye-movement data conveys rich information about underlying mental processes, and that the latter may be inferred from the former. However, most related studies rely on spatial information about which different areas of visual stimuli were looked at, without considering the order in which this occurred. Although powerful algorithms for making pairwise comparisons between eye-movement sequences (scanpaths) exist, the problem is how to compare two groups of scanpaths, e.g., those registered with vs. without an experimental manipulation in place, rather than individual scanpaths. Here, we propose that the problem might be solved by projecting a scanpath similarity matrix, obtained via a pairwise comparison algorithm, to a lower-dimensional space (the comparison and dimensionality-reduction techniques we use are ScanMatch and t-SNE). The resulting distributions of low-dimensional vectors representing individual scanpaths can be statistically compared. To assess if the differences result from temporal scanpath features, we propose to statistically compare the cross-validated accuracies of two classifiers predicting group membership: (1) based exclusively on spatial metrics; (2) based additionally on the obtained scanpath representation vectors. To illustrate, we compare autistic vs. typically-developing individuals looking at human faces during a lab experiment and find significant differences in temporal scanpath features.
Highlights
It has been long established that human eye movement behavior is determined by the properties of the objects that are looked at, and by factors related to the observer, i.e., that they are subject to ‘top-down’ influences independent of the ‘bottom-up’, stimulus-driven effects [1]
We wanted to test if the distributions of the t-distributed stochastic neighbor embedding (t-SNE) dimension-reduced points obtained for autism spectrum disorder (ASD) vs. typically developing (TD) subjects, depicted in Figure 2, were significantly different
A similar result was obtained for the right eye. This suggests that the ASD and TD subjects’ scanpath representation points were distributed differently, which in turn indicates a likely difference between the original sets
Summary
It has been long established that human eye movement behavior is determined by the properties of the objects that are looked at, and by factors related to the observer, i.e., that they are subject to ‘top-down’ influences independent of the ‘bottom-up’, stimulus-driven effects [1]. Eye movement measurements recorded with eye-tracking camera devices, typically head-mounted or attached underneath computer screens, can be used to learn many things about the observer. They can help predict the viewer’s expertise [2] or cognitive capacity [3]. Even state-of-the-art analyses of this type are typically based on spatial but not temporal eye movement information, i.e., on which parts of an image were looked at, but not on when and in what order this has occurred.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
