Hybrid Learning Model Analytics to Predict Learning Style Behavior Clusters of Post-COVID-19 Learners in Higher Education

Hybrid Learning Model Analytics to Predict Learning Style Behavior Clusters of Post-COVID-19 Learners in Higher Education
  IJETT-book-cover           
  
© 2023 by IJETT Journal
Volume-71 Issue-12
Year of Publication : 2023
Author : Kanakarn Phanniphong, Wongpanya S. Nuankaew, Patchara Nasa-Ngium, Pratya Nuankaew
DOI : 10.14445/22315381/IJETT-V71I12P219

How to Cite?

Kanakarn Phanniphong, Wongpanya S. Nuankaew, Patchara Nasa-Ngium, Pratya Nuankaew, "Hybrid Learning Model Analytics to Predict Learning Style Behavior Clusters of Post-COVID-19 Learners in Higher Education," International Journal of Engineering Trends and Technology, vol. 71, no. 12, pp. 195-200, 2023. Crossref, https://doi.org/10.14445/22315381/IJETT-V71I12P219

Abstract
The impact of COVID-19 has forced the learning process to be organized into a hybrid learning environment that requires online and onsite learning services. Therefore, this research has three main objectives: 1) to cluster learners corresponding to learners' learning behaviors with a hybrid learning model, 2) to generate a predictive model for learner learning behavior clusters, and 3) to test the effectiveness of a predictive model for learning behavior clusters. The population and research sample consisted of 24 students enrolled in the course 221203[1] Technology for Business Application at the School of Information and Communication Technology, University of Phayao, in the second semester of the 2022 academic year. Research tools using supervised and unsupervised machine learning include K-Means, Decision Tree, Naïve Bayes, KNearest Neighbors (KNN), Neural Networks, Generalized Linear Model, and Support Vector Machine. The cross-validation approach and confusion matrix techniques were used to test the model with four metrics: Accuracy, Precision, Recall, and F1- Score. The research results showed that the learner clustering was appropriate with three clusters and consistent with the learning achievement of the learners. In addition, it was found that the cluster prediction model had a very high level of accuracy, with an accuracy of 96.67% and an S.D. of ±10.54%. Therefore, disseminating research findings in the public interest is appropriate

Keywords
Educational data mining, Hybrid learning model, Learning analytics, Learning styles, Post-COVID-19.

References
[1] Mohammod Moninoor Roshid, and Prodhan Mahbub Ibna Seraj, “Interrogating Higher Education’s Responses to International Student Mobility in the Context of the COVID-19 Pandemic,” Heliyon, vol. 9, no. 3, pp. 1-12, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Ritika Mahajan et al., “COVID-19 and Management Education: From Pandemic to Endemic,” The International Journal of Management Education, vol. 21, no. 2, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Attasit Srisubat et al., “Effectiveness of Favipiravir Monotherapy in the Treatment of COVID-19: Real World Data Analysis from Thailand,” The Lancet Regional Health - Southeast Asia, vol. 11, pp. 1-7, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[4] N. Leelawat et al., “Twitter Data Sentiment Analysis of Tourism in Thailand During the COVID-19 Pandemic using Machine Learning,” Heliyon, vol. 8, no. 10, pp. 1-11, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Catarina Félix de Oliveira et al., “How Does Learning Analytics Contribute to Prevent Students’ Dropout in Higher Education: A Systematic Literature Review,” Big Data and Cognitive Computing, vol. 5, no. 4, pp. 1-33, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Marzieh Karimi-Haghighi, Carlos Castillo, and Davinia Hernández-Leo, “A Causal Inference Study on the Effects of First Year Workload on the Dropout Rate of Undergraduates,” International Conference on Artificial Intelligence in Education, pp. 15-27, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Joana R. Casanova et al., “Dimensionality and Reliability of a Screening Instrument for Students at Risk of Dropping Out from Higher Education,” Studies in Educational Evaluation, vol. 68, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Saiful Amin et al., “The Effect of Problem-Based Hybrid Learning (PBHL) Models on Spatial Thinking Ability and Geography Learning Outcomes,” International Journal of Emerging Technologies in Learning, vol. 15, no. 19, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Natela Doghonadze, Tamari Dolidze, and Natia Vasadze, “Face-to-Face, Hybrid and Online English as a Foreign Language Learning Efficiency in Higher Education (Georgian and Italian students’ views),” Journal of Education in Black Sea Region, vol. 7, no. 1, pp. 120-143, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Bambang Hariadi et al., “Hybrid Learning by Using Brilian Applications as One of the Learning Alternatives to Improve Learning Outcomes in College,” International Journal of Emerging Technologies in Learning, vol. 14, no. 10, pp. 1-10, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Pratya Nuankaew, Patchara Nasa-Ngium, and Wongpanya S. Nuankaew, “Self-Regulated Learning Styles in Hybrid Learning Using Educational Data Mining Analysis,” 2022 26th International Computer Science and Engineering Conference (ICSEC), pp. 208-212, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Greg Hamerly, and Jonathan Drake, “Accelerating Lloyd’s Algorithm for K-Means Clustering,” Partitional Clustering Algorithms, pp. 41-48, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Raza Hasan et al., “Student Academic Performance Prediction by Using Decision Tree Algorithm,” 2018 4th International Conference on Computer and Information Sciences (ICCOINS), pp. 1-5, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Jingnian Chen et al., “Feature Selection for Text Classification with Naïve Bayes,” Expert Systems with Applications, vol. 36, no. 3, pp. 5432-5435, 2009.
[CrossRef] [Google Scholar] [Publisher Link]