MODELING THE CLASSIFIER OF ONLINE LEARNING EFFECTIVENESS USING MACHINE LEARNING

Abstract

The COVID-19 pandemic that hits almost all countries in the world has caused extraordinary changes, including education. To minimize the spread of the virus, educational institutions are forced to conduct online teaching and learning processes. Online learning using certain media and technology has been initiated and implemented long before the pandemic. However, their effectiveness has not been fully understood. This study aims to model a classifier to determine the effectiveness of online learning based on eight determinants. It also compared the three algorithms, i.e., Support Vector Machine, Naïve Bayes, and Decision Tree. The size of the dataset was 400. It was collected via an online survey. The respondents were undergraduate students from several higher education in Indonesia. The result showed that Naïve Bayes and Decision Tree have the same accuracy, i.e., 93.3%, slightly higher than Support Vector Machine of 91.7%. Based on the precision and recall value, Naïve Bayes achieved the highest precision and recall value of 93.2% and 93.9%, respectively. © 2022 ISSN.

Keywords

Author Keywords

Machine Learning online learning Academic performance Effectiveness Classifier modeling Ease of navigation

Index Keywords

Author Affiliations

Department of Electrical Engineering and Information Technology, Universitas Gadjah Mada, Yogyakarta, Yogyakarta, Indonesia

Department of Data Science, Universitas Teknologi Yogyakarta, Yogyakarta, Java, Indonesia

Funding & Acknowledgements

No funding information

References 10 References

1 Murad, Dina Fitria, The Impact of the COVID-19 Pandemic in Indonesia (Face to face versus Online Learning), Proceeding - 2020 3rd International Conference on Vocational Education and Electrical Engineering: Strengthening the framework of Society 5.0 through Innovations in Education, Electrical, Engineering and Informatics Engineering, ICVEE 2020, (2020)

2 Edy, Duwi Leksono, Revisiting the Impact of Project-Based Learning on Online Learning in Vocational Education: Analysis of Learning in Pandemic Covid-19, 4th International Conference on Vocational Education and Training, ICOVET 2020, pp. 378-381, (2020)

3 Fire Futuristic Implementations of Research in Education, (2020)

4 Kaur, Parneet, Affective state and learning environment based analysis of students’ performance in online assessment, International Journal of Cognitive Computing in Engineering, 2, pp. 12-20, (2021)

5 Microprocess Microsyst, (2020)

6 Wu, Jiun Yu, Learning analytics on structured and unstructured heterogeneous data sources: Perspectives from procrastination, help-seeking, and machine-learning defined cognitive engagement, Computers and Education, 163, (2021)

7 Xu, Xing, Prediction of academic performance associated with internet usage behaviors using machine learning algorithms, Computers in Human Behavior, 98, pp. 166-173, (2019)

8 Saha, Avijit, The mental impact of digital divide due to COVID-19 pandemic induced emergency online learning at undergraduate level: Evidence from undergraduate students from Dhaka City, Journal of Affective Disorders, 294, pp. 170-179, (2021)

9 Rahmad, Fauzi, Performance Comparison of Anti-Spam Technology Using Confusion Matrix Classification, IOP Conference Series: Materials Science and Engineering, 879, 1, (2020)

10 Öztürk, Tülin, Automated detection of COVID-19 cases using deep neural networks with X-ray images, Computers in Biology and Medicine, 121, (2020)

MODELING THE CLASSIFIER OF ONLINE LEARNING EFFECTIVENESS USING MACHINE LEARNING

How to Cite