A Compatible Model for Hybrid Learning and Self-regulated Learning During the COVID-19 Pandemic Using Machine Learning Analytics

Educational models and learning styles are essential and have an evolutionary necessity for the education industry. As a result, the research has identified three objectives: (1) to study the context of hybrid learning management with self-regulated learning style strategies during the COVID-19 pandemic, (2) to develop a data science model for hybrid learning management with self-regulated learning style strategies during the COVID-19 pandemic, and (3) to study the students’ learning achievements with the developed model. The data collection was the 44 higher education students who controlled the self-regulated learning styles in hybrid learning situations during the COVID-19 pandemic at the School of Information and Communication Technology, the University of Phayao. The research tool consisted of statistical and supervised machine learning tools based on descriptive and predictive analytics principles. The model performance evaluation employed a confusion matrix and cross-validation techniques for testing. The research findings show that learners’ contexts in the COVID-19 pandemic have different learning behaviors and achievement styles under hybrid learning management strategies. The researchers successfully developed a prototype model for predicting learners’ learning achievement for hybrid learning management with self-regulated learning style strategies. The results of this research can further be used as a guideline for educational management in unusual situations to improve the quality of learners and the academic industry.