Predicting adoption of AI-driven e-learning systems in Bangladesh’s public higher education: A survey-based machine learning approach

Abstract

Over the last few years, the rapid growth of information technology (IT) has changed how digital learning systems are integrated into public higher education systems. There still seems to be a lack of understanding of the factors that affect the successful implementation of artificial intelligence (AI)- driven systems in public higher education systems. Due to inadequate infrastructure, varying levels of digital literacy among users, and a lack of empirically based models to predict system outcomes, many public higher education systems have been unable to implement AI-driven systems in their eLearning environments. This paper aims to take the first step toward developing a predictive model of AI-driven eLearning system adoption. To do this, a machine learning approach will be used to develop the model. This study employed a fully quantitative method involving 287 academic staff and students from five public higher education institutions in Bangladesh. The findings identified three factors of the Institutional eLearning Framework as the most significant predictors of eLearning adoption: perceived usefulness of eLearning, institutional support, and data quality of the eLearning system. The main contribution of this study to the body of research on the higher education system is to link one or more established theories of acceptance with predictive analysis models, thereby developing a tool that can be put in the hands of a system planner.