ML-Based Classification of Eye Movement Patterns During Reading Using Eye Tracking Data from an Apple iPad Device

EasyChair Preprint 6150

Abstract

Eye movements in reading can provide important information about readers’ perception of texts and, with appropriate algorithms, about the level of their understanding of what is written. Both digital learning and professional training require processing of large volumes of information, mostly in the text format. Management and control of students’ or trainees’ levels of perception in reading can be accomplished with the use of technology, assessing attention, engagement, understanding, cognitive load and tiredness of readers. These metrics can potentially be inferred from eye tracking data during reading a text. For this task it is important to utilize features of mass-market consumer devices. For example, the latest version of Ipad Pro with a standard iOS operating system has an embedded eye tracker, and thus it provides opportunities for mass adoption in the educational and training settings. Authors of this work built a stable algorithm for detecting saccades and fixations in noisy eye tracking data recorded by iPad Pro 11" and achieved certain progress in applying a machine-learning algorithm for classifying eye movement patterns in reading. The results could be used for creating an interactive reader’s assistant in the format of an iOS application.

Keyphrases: eye-tracking data, machine learning, reading, text perception

@booklet{EasyChair:6150,
  author    = {Victor Anisimov and Konstantin Сhernozatonsky and Andrey Pikunov and Shedenko Ksenia and Daria Zhigulskaya and Arsen Revazov},
  title     = {ML-Based Classification of Eye Movement Patterns During Reading Using Eye Tracking Data from an Apple iPad Device},
  howpublished = {EasyChair Preprint 6150},
  year      = {EasyChair, 2021}}