Features in eye-tracking data for classification: A systematic literature review

Eye-tracking is a technology to measure and determine an individual's eye movements and eye positions. The eye data can be collected and recorded using an eye-tracker. Eye-tracking data offers unprecedented insights into human actions and environments, digitizing how people communicate with computers, and providing contributions in computer science such as the research on classification. The objective of this paper was to review what features can be obtained from eye-tracking data for classification. We performed a systematic literature review (SLR) covering the eye-tracking studies in classification published from 2016 to the present. In the search process, we used 3 independent electronic databases such as IEEE Xplore, ACM, and ScienceDirect digital libraries. We concluded that there are many researchers who used features from eye-tracking data for classification tasks. The features contained information that can be utilized to classify the difference. There are several features found from eyetracking such as pupil size, saccade, fixations, velocity, blink, pupil position, EOG, and gaze point. Fixation is the most commonly used feature among the studies found.