Close

Presentation

Time Pressure Detection in a Visual Search Task Using Eye Tracking Metrics: A Virtual Reality Study
DescriptionVisual search involves directing attention to locate specific objects amidst visual stimuli. Visual search performance is affected by many factors, one of which is time pressure. Detecting time constraints in real-time is vital for timely interventions to counter performance decline. Previous studies primarily focused on stress detection, relying on subjective or stress-correlated measures, rather than directly identifying the presence of a time constraint. However, stress responses vary individually and may not align with performance levels; thus, objective measures are needed. This study aims to detect time pressure in a naturalistic visual search task using eye tracking metrics. Forty participants searched for objects in virtual reality under varied timing conditions and reward incentives while eye tracking data was collected. Thirteen metrics were calculated and used to train six classifiers on detecting time pressure. The support vector machine (SVM) was the best-performing model with 74% accuracy and 0.82 AUROC.
Event Type
Lecture
TimeFriday, September 13th8:30am - 8:50am MST
LocationFLW Salon I
Tracks
Extended Reality