Automated Reading Detection in an Online Exam
Loading...
Date
2022
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
International Journal of Emerging Technologies in Learning (iJET)
Abstract
In this article we study a deep learning-based reading detection problem in an online exam proctoring. Pandemia-related restrictions and lockdowns lead many educational institutions to go online learning environment. It brought the exam integrity challenge to an online test-taking process. While various commercial exam proctoring solutions were developed, the online proctoring challenge is far from being fully addressed. This article is devoted to making a contribution to the exam proctoring system by proposing an automated test-taker reading detection method. To this end, we obtain our own dataset of short video clips that resemble a real online examination environment and different video augmentation methods utilized to increase the training dataset. Two different deep learning techniques are adapted for training. The experiments show quite satisfactory results with model accuracy varying from 98.46% to 100%. The findings of the article can help educational institutions to improve their online exam proctoring solutions, especially in language speaking tests.
Description
Keywords
exam proctoring, reading detection, video recognition
Citation
Bakhitzhan K , Kadyrov Sh , Makhmutova A / Automated Reading Detection in an Online Exam / International Journal of Emerging Technologies in Learning (iJET) / 2022