Inferring intent in eye-based interfaces: tracing eye movements with process models

  • Authors:
  • Dario D. Salvucci

  • Affiliations:
  • Department of Computer Science, Carnegie Mellon University, Pittsburgh, PA

  • Venue:
  • Proceedings of the SIGCHI conference on Human Factors in Computing Systems
  • Year:
  • 1999

Quantified Score

Hi-index 0.01

Visualization

Abstract

While current eye-based interfaces offer enormous potential forefficient human-computer interaction, they also manifest thedifficulty of inferring intent from user eye movements. This paperdescribes how fixation tracing facilitates the interpretation ofeye movements and improves the flexibility and usability ofeye-based interfaces. Fixation tracing uses hidden Markov models tomap user actions to the sequential predictions of a cognitiveprocess model. In a study of eye typing, results show that fixationtracing generates significantly more accurate interpretations thansimpler methods and allows for more flexibility in designing usableinterfaces. Implications for future research in eye-basedinterfaces and multimodal interfaces are discussed.