Back

Present: flexible neuroscience- and technology-driven frameworks for the study of classroom engagement

Shatto, C. L.; Thorpe, J. N.; Friedman, J. S.; Rosario, I. E.; Gu, Z.; Shi, J.; Zhuo, M.; Brown, A.; He, X.; Spagna, A.

2023-06-26 neuroscience
10.1101/2023.06.23.544732 bioRxiv
Show abstract

Classroom engagements impact on academic success is crucial. However, the contributions of affective, cognitive, and behavioral components of engagement remain uncertain. We conducted two studies using non-invasive, research-based approaches to clarify these contributions. Study 1 employed portable EEG headsets to measure cognitive engagement, in-class quizzes assessed content retention, and post-class subjective questionnaires indexed affective engagement by measuring feelings of learning and engagement. Content retention predicted subjective measures, while the EEG theta/beta ratio was negatively related to content retention but positively related to subjective measures. Study 2 featured embedded measures of content retention, confidence, engagement, background knowledge, and indexed behavioral engagement looking at nonverbal behavior quantified via video camera recordings. Confidence and engagement were significantly correlated with each other and with particular facial muscle, gaze direction, and head pose movements. We discuss how these approaches enable real-time studies of classroom engagement and can be integrated to develop neurofeedback interventions.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.