The incorporation of remote learning in higher education has been accelerated since the outbreak of the global pandemic in 2020. Universities have been investing in acquiring equipment and upgrading their network infrastructure in order to keep up with the demand for high quality virtual education.
But are students paying attention in virtual classrooms? If so, how can we know? This is a question that haunts many in academia.
Researchers Jens Madsen and Lucas C. Parra from City College of New York (CCNY) were able to demonstrate how eye tracking can be used to measure the level of attention online using standard web cameras, without the need to transfer any data from people’s computers, thus preserving privacy.
According to the researchers, just by looking at students' eyes they can predict how well students will do on quizzes based on educational videos. It sounds simple. Yet, it requires a great deal of classroom management skills and experience.
This could represent a challenge for beginning teachers. Teachers’ cognition and conceptualizations differ between expert teachers and those just starting their academic career.
"Experienced teachers pay close attention to their students, adjusting their teaching when students seem lost. This dynamic interaction is missing in online education," says Jens Madsen.
"But in our study, we proposed to measure attention to online videos remotely by tracking eye movements and hypothesized that attentive students follow videos similarly with their eyes."
Thus, attention to instructional videos could be assessed remotely by tracking eye movements.
According to the CCNY researchers, they were able to show that inter-subject correlation of eye movements during an educational video presentation is substantially higher for attentive students, and that synchronized eye movement is predictive of individual test scores on the material presented in the video.
The study shows that attentive students have similar eye movements when watching instructional videos and that synchronization of eye movements is a good predictor of individual learning performance.
Measuring synchronization of eye movements while preserving privacy, say the researchers, has the potential to make online education adaptive to attentional state and advance mechanistic studies on the efficiency of different online education formats.
"These findings replicate for videos in a variety of production styles, learning scenarios, and for recall and comprehension questions alike," says Lucas C. Parra. "We were able to reproduce the results using standard web cameras to capture eye movements in a classroom setting, and with over 1,000 participants at home, without the need to transmit user data."
The results in the paper entitled Synchronized Eye Movements Predict Test Scores in Online Video Education, published in the Proceedings of the National Academy of Sciences suggest that online education can be made adaptive to a student's level of attention in real-time.
For the researchers, "the Internet has turned attention into a commodity. With video content increasing online, remote sensing of attention to video at scale may have applications beyond education, including entertainment, advertising, or politics. The applications are limitless."
The videos below show how eye movements can be used to measure the level of attention of students in online education. The researchers also could measure when the students were paying attention.
In the video we see the gaze position of 27 students as red dots while watching educational videos. The traces on the bottom indicate how synchronized eye movements and pupil size are between students at that point in time. When this inter-subject correlation (ISC) is above the pink-shaded area the synchronization is statistically significant.
In the attentive condition, students watch the video normally.
Why are Stars Star-Shaped? Attending Video
In the distracted condition, students are asked to also do a mental arithmetic task, which keeps them distracted.
Why are Stars Star-Shaped? Distracted Video
It is possible to notice that the gaze positions are tightly clustered when attending and spread all over the place when distracted.
The findings of the CCNY study may be rather useful for academics to effectively assess student attention during remote learning.