The construction industry is increasingly harnessing sensing technologies to overcome manual data collection limitations and address the need for advanced data analysis. This places an aggravated demand for associated skills to interpret sensor data. Yet, a substantial gap exists between the level of academic preparation and the actual needs of the industry, leading to an underprepared workforce. In this study, ActionSens, a Block-Based Programming Environment, is implemented as an educational tool that combines sensor data from Inertial Measurement Units with machine learning algorithms. This integration enables the classification of construction activities, offering construction students a platform to explore and learn about sensor data analytics. However, in a pedagogical setting, an enhanced learning experience can be achieved through the integration of automated classification models that intelligently detect learners’ focus with the potential to provide context-specific support. This study utilizes 19 construction students’ eye-tracking data to train and evaluate machine learning models to detect learners’ visual focus on specific Areas of Interest within ActionSens. Ensemble, Neural Network, and K-Nearest Neighbor performed the best for both raw and SMOTE-oversampled datasets. The Ensemble had an edge in recognizing Areas of Interest, achieving top precision, recall, F1-score, and AUC in the oversampled data.