Non-intrusive identification of student attentiveness and finding their correlation with detectable facial emotions

Tasnia Tabassum, Andrew A. Allen, Pradipta De

Research output: Contribution to book or proceedingConference articlepeer-review

17 Scopus citations

Abstract

Teachers use observational cues in the classroom to identify attentiveness of students and guide the pace of their lecture. However, effectiveness of this technique decreases with increasing class size. This paper presented an approach for automating these observational cues from the students' facial expressions and identifying their attentiveness via a neural network machine learning model. Results of the deep learning Convolutional Neural Network model were then compared with the range of confidence values obtained from a cloud-based emotion recognition service to identify the correlations with human observer. Real time videos of students were collected during classes and sample dataset were created for attentive and inattentive students in order to train the machine learning model. This system can be highly useful for inexperienced teachers for early identification of inattentive students in classroom and thereby taking necessary actions to enhance student learning.

Original languageEnglish
Title of host publicationACMSE 2020 - Proceedings of the 2020 ACM Southeast Conference
PublisherAssociation for Computing Machinery, Inc
Pages127-134
Number of pages8
ISBN (Electronic)9781450371056
DOIs
StatePublished - Apr 2 2020
Event2020 ACM Southeast Conference, ACMSE 2020 - Tampa, United States
Duration: Apr 2 2020Apr 4 2020

Publication series

NameACMSE 2020 - Proceedings of the 2020 ACM Southeast Conference

Conference

Conference2020 ACM Southeast Conference, ACMSE 2020
Country/TerritoryUnited States
CityTampa
Period04/2/2004/4/20

Scopus Subject Areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Hardware and Architecture
  • Software

Keywords

  • Amazon Rekognition
  • Classroom Observational Study
  • Convolutional Neural Network
  • Deep Learning
  • Facial Emotion Detection
  • Machine Learning

Fingerprint

Dive into the research topics of 'Non-intrusive identification of student attentiveness and finding their correlation with detectable facial emotions'. Together they form a unique fingerprint.

Cite this