Identifying User Tasks in Map Based-Pedestrian Navigation from Eye Tracking Data

Abstract

Eye movement data convey a wealth of information that can be used to inspect human behavior and cognitive processes. In this study, we explored to identify user tasks in map-based pedestrian navigation using eye movement data. We collected 44 participants´ eye movement data by conducting an eye tracking experiment in real-world environments. We trained and cross-validated a Random Forests classifier to classify 7 common user tasks using 564 features. The preliminary results show the classifier can achieve an overall accuracy of 48%.