NORMA eResearch @NCI Library

Machine Learning and Eye-tracking Framework to Detect Engagement in Online Learning

Chandrasekar, Yogalakshmi (2022) Machine Learning and Eye-tracking Framework to Detect Engagement in Online Learning. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


This research proposes a machine learning framework that helps to identify the online learning engagement of students. The biggest challenge is to detect the cognitive processes of the students, whether they are engaged in an online learning ecology or in a passive phase that is: not involved in the lecture. This framework combines machine learning model with eye-tracker device. A lab video on android app development is shown to students from all the academic background for 7 minutes. Wherein, the participant’s eye movements are tracked using an eye tracking device. The experiment begins by filling the participants fill out the personality questionnaire to access their cognitive processes, learning ability , and alertness level. Followed by that participants answered multiple choice questionnaire based on the tutorial video. The video recorded in the eye tracking devices is processed to prepare it ready for analysing it in the machine learning models. In order to detect correlation between the cognitive presence of the students and engagement. The data collected from the eye-tracking device and the questionnaire is used in the research to get the result. The models are evaluated based on accuracy, balanced accuracy, ROC AUC (receiver operating characteristic ), F1 score. The model KNN K-Nearest Neighbour has been consistent across all the 3 experiments and provided accuracy ranges from 67 to 79 percentage. The algorithm Logistic Regression has outperformed all the other model in experiment 3 with the highest accuracy of 89 percentage, precision: 1, Recall: 0.75, F1-score: 0.86 and 91 percentage weighted average.

Item Type: Thesis (Masters)
Uncontrolled Keywords: Machine learning; online learning; cognitive presence; Eye tracking; engagement detection
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
L Education > LC Special aspects / Types of education > E-Learning
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 19 Jan 2023 16:13
Last Modified: 06 Mar 2023 15:39

Actions (login required)

View Item View Item