A Real-Time Eye Tracking System for Predicting and Preventing Postcompletion Errors

Abstract

Procedural errors occur despite the user having the correct knowledge of how to perform a particular task. Previous research has mostly focused on preventing these errors by redesigning tasks to eliminate error prone steps. A different method of preventing errors, specifically postcompletion errors (e.g., forgetting to retrieve the original document from a photocopier), has been proposed by Ratwani, McCurry, and Trafton (2008), which uses theoretically motivated eye movement measures to predict when a user will make an error. The predictive value of the eye-movement-based model was examined and validated on two different tasks using a receiver-operating characteristic analysis. A real-time eye-tracking postcompletion error prediction system was then developed and tested; results demonstrate that the real-time system successfully predicts and prevents postcompletion errors before a user commits the error.

Notes

¹The time measure was originally calculated by Ratwani et al. (2008) as the sum of fixation durations immediately preceding the postcompletion action. The logistic regression model was also run using clock time, and the results were consistent; the time measure was not a significant predictor of postcompletion errors.

Acknowledgments. We thank Malcolm McCurry for designing the experimental tasks and programming the real-time eye-tracking system and Kristina O'Connell and Jenny Sousk for help with data collection. We also thank Richard Pew and Mike Byrne for comments on this manuscript.

Support. This work was supported by project number N0001409WX20173 from the Office of Naval Research to Greg Trafton and by a fellowship from the National Research Council to Raj Ratwani.

HCI Editorial Record. First received July 8, 2009. Revisions received January 15, 2010 and May 24, 2010. Accepted by Richard Pew. Final manuscript received June 27, 2010. — Editor