Bioindicators of Attention Detection in Online Learning Environments

Online classrooms have gained significant prominence in the post-COVID era. While online classes offer advantages, they introduce more distractions that can compromise students’ attention to the learning material. Additionally, instructors can find it challenging to gauge student attentiveness when limited to a camera view. The proposed study aims to identify body motion and physiological indicators that can be used to gauge participants’ attention in the online meetings. The study explored a set of indicators, including body motion, heart rate, skin temperature, and eye movement. Twenty participants participated in four 30-min long trials consisting of one control and three experimental trials with varying degrees of distractions. Statistical and machine-learning approaches were employed to identify the key indicators of attention. The results reveal that the eye movement, and heart rate showed statistically significant differences between the trials, while the remaining indicators displayed no significant differences.