A Novel Eye Movement Data Transformation Technique that Preserves Temporal Information: A Demonstration in a Face Processing Task
Michał Król , Magdalena Król
AbstractExisting 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 di�erences 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.
|Journal series||Sensors, [SENSORS-BASEL], ISSN 1424-8220, (N/A 100 pkt)|
|Publication size in sheets||0.5|
|Keywords in English||eye tracking; scanpath comparison; dimensionality reduction; machine learning; autism; face perception|
|ASJC Classification||; ; ;|
|Publication indicators||: 2016 = 1.393; : 2017 = 2.475 (2) - 2017=3.014 (5)|
|Citation count*||2 (2020-06-30)|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.