This paper introduces a machine learning-based eye tracking method using a smartphone's front-facing camera, achieving accuracy comparable to specialized mobile eye trackers at a fraction of the cost. The researchers validated their method by replicating key findings from previous eye movement studies and demonstrated its potential for assessing reading comprehension difficulty and other applications.

This study was funded by Google LLC and/or a subsidiary thereof ('Google'). N.V., N.D., J.H., V.R., P.X., M.S., K.K., and V.N. are employees of Google. E.S., K.R., and L.G. were interns at Google.

This paper presents a novel and impactful method for smartphone-based eye tracking that achieves accuracy comparable to expensive specialized equipment. The methodology is rigorously validated through replicating established findings in oculomotor research and saliency analysis, along with showcasing potential in new applications like reading comprehension assessment. While limitations exist regarding ecological validity, temporal resolution, and sensitivity to environmental factors, the affordability, scalability, and potential societal benefits of this approach warrant a strong rating. The declared conflict of interest with Google is acknowledged and considered in the rating.