Prediction of Student Adaptability Level in e-Learning using Machine and Deep Learning Techniques

Download Edit this record How to cite View on PhilPapers
Abstract
E-learning is an educational model in which the lectures can be taught at the same time using technical material without time and space barriers. E-learning has gained its popularity during the Covid-19 pandemic era and has been applied as a valid educational model in all educational levels. Due to the sudden pandemic measures, e-learning has brought about a lot of technical problems at unprepared educational institutions against the pandemic. It is important for the decision makers of educational institutions to get feedback about the effectiveness of e-learning so that they can take further steps to make it more beneficial for the students. In this paper, a dataset was collected from Kaggle depository for the adaptability level in e-Learning. In order to find how effective e-learning, a group of machine and deep learning algorithms were applied to predict the adaptability level of the students to e-learning. The best machine-learning algorithm was Decision Tree Classifier with Accuracy (92.00%), Precision (92.00%), Recall (92.00%), F1-score (92.00%); however, the proposed deep learning algorithm achieved Accuracy (94.67%), Precision (94.80%), Recall (94.70%), F1-score (94.61%).
Categories
(categorize this paper)
PhilPapers/Archive ID
ALKPOS
Upload history
Archival date: 2022-06-02
View other versions
Added to PP
2022-06-02

Downloads
124 (#48,839)

6 months
124 (#4,747)

Historical graph of downloads since first upload
This graph includes both downloads from PhilArchive and clicks on external links on PhilPapers.
How can I increase my downloads?