Combining eye tracking with other process measures such as machine vision features provides useful information about student engagement¶

Claim · All claims
Evidence · 1 study · review r2 · q2
Currency · newest study 2021 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? A machine vision and machine learning analysis of eye gaze, head pose, and facial expression from classroom video correlated with manual coding and predicted self-reported cognitive engagement and involvement. → Kaakinen 2021

Evidence¶

Kaakinen 2021¶

Kaakinen, J. K. (2021). What Can Eye Movements Tell us about Visual Perception Processes in Classroom Contexts? Commentary on a Special Issue. Educational Psychology Review, 33, 169-179. https://doi.org/10.1007/s10648-020-09573-7

q2 · i? · review · r2

The commentary reports, citing Goldberg et al. in the Special Issue, a machine learning approach using eye gaze, head pose, facial expressions, and peer synchronization as model features. The automated results "correlated with manual coding" and predicted self-reports. No correlation coefficients are printed.

"The results were promising: the results of the automated analysis correlated with manual coding of the videos, and predicted self-reported cognitive engagement and involvement."

Discussion¶

Related Claims¶

• Eye tracking can be used to study student engagement, teacher expertise, and teacher-student interaction in naturalistic classroom contexts — a broader claim this one bears on
• Machine learning measures of student engagement correlate moderately to highly with manual ratings, but manual ratings better predict self-reported engagement — related
• Certain multimodal data combinations improve predictive model performance, with audio plus eye-tracking data most effective in one K–8 study — related
• Facial features of negative emotions predict low rapport, but additional modalities added no predictive power — related