Conference Tracks
Teaching with Technology – Research
Abstract
Teachers use observational cues in the classroom to identify attentiveness of students and guide the pace of their lecture, however, with increased class sizes it has become less effective. This paper presents an approach for automating these observational cues of the students, identifying the attentiveness of students. The approach includes a neural network machine learning model to detect whether a student is attentive or inattentive depending on their facial expressions. Results of the deep learning CNN model were compared with the range of confidence values obtained from a cloud-based emotion recognition service to identify the correlations with the human observer.
Session Format
Poster
1
Location
Harborside Ballroom East
Recommended Citation
Tabassum, Tasnia; Allen, Andrew; and De, Pradipta, "Non-Intrusive Identification of Student Attentiveness and Finding their Correlation with Detectable Facial Emotions" (2020). SoTL Commons Conference. 15.
https://digitalcommons.georgiasouthern.edu/sotlcommons/SoTL/2020/15
Non-Intrusive Identification of Student Attentiveness and Finding their Correlation with Detectable Facial Emotions
Harborside Ballroom East
Teachers use observational cues in the classroom to identify attentiveness of students and guide the pace of their lecture, however, with increased class sizes it has become less effective. This paper presents an approach for automating these observational cues of the students, identifying the attentiveness of students. The approach includes a neural network machine learning model to detect whether a student is attentive or inattentive depending on their facial expressions. Results of the deep learning CNN model were compared with the range of confidence values obtained from a cloud-based emotion recognition service to identify the correlations with the human observer.
