Talk · International Conference on Intelligent Sustainable Systems · March 12, 2025
GazeBTL: Webcam-based Eye Tracking to Analyze Bloom’s Taxonomy Levels in Student Assessments
Hemanth Ramasubbu, Sreeharsha Sadhu, Mehul Singh Bhakuni, C. Jyotsna, J. Amudha
Abstract
The high cost and limited accessibility of traditional eye-tracking hardware present challenges for widespread use in educational assessments, where insights into student engagement and cognitive processes could enhance learning outcomes. This study proposes a model GazeBTL, a scalable, webcam-based eye-tracking approach utilizing the RealEye platform to capture and analyze students’ gaze behavior during assessments. By correlating gaze patterns with Bloom’s Taxonomy Levels (BTL), the cognitive demand of unseen questions is predicted. The results indicate that the ensemble ResNet50 Convolutional Neural Network (CNN) achieved an accuracy of 76.12%, surpassing traditional machine learning and standalone CNN models. Despite limitations in precision compared to traditional systems, this accessible approach demonstrates the potential for personalized learning and adaptive assessments. These findings pave the way for integrating webcam-based eye tracking into large-scale educational environments.
More by Jyotsna Chandrasekharan
- Optimization of Lotka-Volterra Equations using Ant Colony OptimizationInternational Conference on Recent Advancement in Electrical, Computer and Communication Technologies · 2026
- Comparative Analysis of Deep Learning Models for Visual Classification of Terrestrial and Extraterrestrial Rock ImageIEEE International Conference on AI Engineering and Innovations · 2026 · Citations: 1
- Real Time Screen Based Gaze Estimation Using MediaPipe and Machine Learning ModelsIEEE International Conference on AI Engineering and Innovations · 2026
- ECG Analysis for Myocardial Infarction Detection via Deep LearningProcedia Computer Science · 2026