Machine Learning Models to Predict Individual Cognitive Load in Collaborative Learning: Combining fNIRS and Eye-Tracking Data

Effectively leveraging cognitive load predictions helps optimize collaborative learning design and implementation. This study explored the feasibility of predicting individual learners’ cognitive load during collaborative learning using a combination of functional near-infrared spectroscopy (fNIRS) and eye-tracking data. A total of 188 valid collaborative events collected from 78 graduate students who engaged in three collaborative ideation tasks were analyzed using various machine learning algorithms applied to classify cognitive load levels. Nine features, derived from both fNIRS and eye-tracking data, were used as input for the models. Results demonstrated that machine learning models could accurately predict individual cognitive load, with the Random Forest model achieving the highest performance (F1 score = 0.84). Furthermore, the integration of fNIRS and eye-tracking data significantly enhanced predictive performance, with the multimodal model achieving an F1 score 0.87—outperforming the eye-tracking-only model (F1 = 0.79) by 8% and the fNIRS-only model (F1 = 0.68) by 19%. Analysis of feature importance revealed that “Total Fixation Duration”, “Average Inter-Fixation Degree”, and prefrontal cortex activity were among the strongest predictors of learners’ cognitive load. These findings have implications for understanding cognitive load dynamics and designing effective collaborative learning environments and human–computer interfaces.