Predicting Cartographic Symbol Location with Eye-Tracking Data and Machine Learning Approach.

Abstract

Visual search is a core component of map reading, influenced by both cartographic design and human perceptual processes. This study investigates whether the location of a target cartographic symbol-central or peripheral-can be predicted using eye-tracking data and machine learning techniques. Two datasets were analyzed, each derived from separate studies involving visual search tasks with varying map characteristics. A comprehensive set of eye movement features, including fixation duration, saccade amplitude, and gaze dispersion, were extracted and standardized. Feature selection and polynomial interaction terms were applied to enhance model performance. Twelve supervised classification algorithms were tested, including Random Forest, Gradient Boosting, and Support Vector Machines. The models were evaluated using accuracy, precision, recall, F1-score, and ROC-AUC. Results show that models trained on the first dataset achieved higher accuracy and class separation, with AdaBoost and Gradient Boosting performing best (accuracy = 0.822; ROC-AUC > 0.86). In contrast, the second dataset presented greater classification challenges, despite high recall in some models. Feature importance analysis revealed that fixation standard deviation as a proxy for gaze dispersion, particularly along the vertical axis, was the most predictive metric. These findings suggest that gaze behavior can reliably indicate the spatial focus of visual search, providing valuable insight for the development of adaptive, gaze-aware cartographic interfaces.