When standard eye tracking techniques developed in the context of large-screen devices are applied to applications on mobile devices, the results are often erroneous. For example, when the true percentage of viewers (as identified manually) that look at a profile picture is 100%, standard eye techniques typically underestimate the eye fixation behavior, returning a much smaller value. Many mobile applications utilize a feed interface that involves moving targets as the user scrolls the feed. This disclosure describes techniques that use appropriate temporal, spatial, and velocity-based parameters to define fixation by area of interest (AOI) size for mobile-feed applications. The techniques enable accurate measurement and analysis of visual user behavior during mobile-feed viewing, such as eye-gaze patterns, fixation durations, time to first fixation, percentage of viewers fixated, etc.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Anonymous, "Improved Fixation Filter For Eye Tracking On Small Devices", Technical Disclosure Commons, (August 24, 2020)