Learner Attention Quantification Using Eye Tracking and EEG Signals

Md Shakil Hossain, Dhruv Pandya, Andrew A. Allen, Felix Hamza-Lup, Felix G. Hamza-Lup

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

We adapted an application called Non-Intrusive Classroom Attention Tracking System (NiCATS) that quantifies and generates statistical data based on a student’s attention level while performing various tasks like coding, browsing through websites, or reading lecture notes on computers. This research is focused on understanding how student attentiveness can be measured using eye-tracking (e.g. gaze points) and Electroencephalogram (EEG) signals data. By leveraging the existing NiCATS with new integration of BCI devices we explore the possibilities of identifying correlations of EEG signals with students’ attention during classroom. Two Eye metrics (number of saccades and total fixations) have slight positive correlation with all the EEG bands (theta, alpha, etc.) except the delta band. The result of this analysis is an additional step toward providing instructors feedback on the effectiveness of instructional design as measured by attentiveness of students in their classroom.

Original languageAmerican English
JournalProceedings of the Future Technologies Conference
Volume2
DOIs
StatePublished - Oct 13 2022

Disciplines

  • Computer Sciences

Keywords

  • Brain computer interface
  • Classroom attention tracking
  • Electroencephalogram (EEG)
  • Eye-tracking

Fingerprint

Dive into the research topics of 'Learner Attention Quantification Using Eye Tracking and EEG Signals'. Together they form a unique fingerprint.

Cite this