What is it about?

For this study the research team collected data from eye-trackers as students worked in a computer-lab setting in engineering classes. The students were periodically asked to respond to online questions about their level of attention to the course. Machine learning algorithms were applied to the eye-tracking data and were able to predict student attentiveness to the course with an accuracy of 77%.

Featured Image

Why is it important?

The most important finding of this exploratory study was that the eye-tracking data, which was collected with minimal intrusion, combined with the machine learning algorithms, was able to produce a somewhat accurate predictive model.

Perspectives

Working on this project providing an interesting collaboration between faculties of Education and Engineering working toward ultimately improving instruction at the university-level. The team meetings, which included the lead author (a graduate student) were always engaging and provided an opportunity to discuss learner motivation, research data collections methods, and principles of engineering.

Professor of Instructional Technology Charles B. Hodges
Georgia Southern University

Read the Original

This page is a summary of: Modeling Students' Attention in the Classroom using Eyetrackers, April 2019, ACM (Association for Computing Machinery),
DOI: 10.1145/3299815.3314424.
You can read the full text:

Read

Contributors

The following have contributed to this page