Eye-tracking and questionnaires are typically treated as separate methods for measuring usability and user experience (UX). Recent studies show that machine learning models trained solely on eye movements can predict pragmatic and hedonic quality ratings. Building on this, this study examines which gaze patterns predict usability and UX and whether models can generalize across stimuli. Five models were trained on eye movements from 121 users browsing six websites. A feature-importance analysis revealed that saccadic patterns, such as regressions and successive forward movements, are more associated with UX, whereas longer consecutive saccades are indicative of usability. When trained separately for each website, the best-performing models achieve Matthews Correlation Coefficient scores of 0.751 and 0.780, with only small negative effect sizes on holdout data. Trained across websites, holdout scores dropped to 0.196 for usability and 0.338 for UX, suggesting that cross-stimuli generalizability is limited and, at best, achievable for hedonic interaction aspects.

Scanpaths and eye movements provide insight into how users perceive and interact with digital products. However, most studies assess user states using stimulus-dependent metrics, like fixations or areas of interest (AOIs). This paper examines whether stimulus-independent saccadic transitions — gaze movements not tied to predefined stimulus elements — carry predictive information about user states and experiences. To do so, eye-tracking data and perceived usability and UX ratings from a study with 121 participants interacting with websites were analyzed. Saccadic transitions were extracted from the scanpaths and analyzed using machine learning models to identify transition patterns predictive of the user ratings. Results show that models predict perceived usability and UX most accurately when saccade transitions are grouped into the eight inter-cardinal directions and further differentiated by median saccade length. This demonstrates that even brief, often-overlooked gaze shifts within the stimulus might provide valuable insight into how users perceive websites.

Eye-tracking is increasingly used in human–computer interaction (HCI) research to measure visual attention and user interaction. More recently, established eye-tracking metrics have been used as inputs to machine learning models. However, the transformation of traditional eye movement metrics into machine-learning-compatible features is rarely discussed in the literature. This limits the reproducibility and interpretability of how different eye-tracking metrics influence classification outcomes, particularly for researchers new to data-driven modeling. This paper provides a survey of how established third- and fourth-order scanpath metrics can be systematically converted into features suitable for classification and regression models. Building on existing metric categorizations, common gaze metrics are linked to concrete feature conversion techniques, including discretization, matrix unfolding, n-gram analysis, and scanpath segmentation.

In the course Eye Tracking in Engineering Science, students develop a variety of skills. These competencies include both, theoretical knowledge and practical experience: in empirical research (i.e., the design of experiments and the writing of research papers), in eye tracking technology, and in applying computer science and statistics for data analysis. This competence building is done with a teaching concept based on pair-teaching and research-based learning - described in detail in the present article.