Exploring Useful Teacher Roles for Sustainable Online Teaching in Higher Education Based on Machine Learning

Abstract

The COVID-19 emergency necessitated a rapid transition to online teaching by university lecturers. Hence, lecturers need to develop and reorganize their instructions and adjust their teaching roles and activities to the technological demands so as to further facilitate their continuous usage of technological systems after the crisis. Based on the behaviors of lecturers who utilized a particular teaching system—Rain Classroom—during school closure, this study aimed to predict their retention of online teaching beyond lockdown. Classical machine-learning classifiers were adopted to make predictions, most of which had an accuracy greater than 73%. Moreover, through a byproduct of these algorithms—feature scoring—we also aimed to determine the prime activities and roles that have strong relationships with lecturers’ retention dispositions. The domain meaning of feature scoring was revealed based on a specific conceptualization of perceived usefulness and the TAM model, which further enlightened system devisers about strategies to improve technological quality. A coevolution mechanism was thus formed, both providing guidance for lecturers in changing their overt behaviors with respect to online teaching and supporting the customization of system functionalities, so as to foster the mutual adaption of teachers’ pedagogies and artifact affordances. The findings, concerning useful teaching roles (namely, learning assessment, guiding technology usage, and learning support) and activities (such as in-class exercises, monitoring of students’ attendance, formal testing, etc.), are corroborated by evidence from other reports in the literature.