Mobile Learning Technologies as drivers of School Enrolment Levels in South Africa: A Policy Simulation Experiment using Machine Learning-Driven Dynamic Autoregressive Distributed Lag Model
Authors: Muazu, F.A., Adedoyin, F., Dogan, H., Whittington, P. and Mavengere, N.
Journal: 37th International BCS Human-Computer Interaction Conference, BCS HCI 2024
Pages: 87-99
DOI: 10.14236/ewic/BCSHCI2024.8
Abstract:This study addresses the imperative challenge of enhancing school enrolment in South Africa by investigating the dynamics of mobile learning technologies, internet access, and key socio-economic variables. Spanning 35 years (1998–2022), the research draws from the National Digital and Future Skills Strategy, aiming to provide insights into the factors influencing educational access. Employing an analytical framework that integrates Autoregressive Distributed Lag (ARDL), dynamic ARDL (dynARDL) simulations, and Kernel-based Regularized Least Squares (KRLS) machine learning, the study finds that economic prosperity, as represented by real GDP per capita, positively influences secondary school enrolment. Mobile phone subscribers emerge as a significant driver, emphasizing the transformative potential of digital technologies. Surprisingly, an inverse relationship between internet users and enrolment prompts a reassessment of the role of internet access in education. The dynARDL simulations introduce counterfactual shocks, highlighting the positive impact of a 10% increase in mobile subscribers and the nuanced consequences of changes in internet users. KRLS analysis reinforces the significance of economic indicators, digital technologies, and human development in shaping enrolment. Drawing policy implications, the study advocates targeted investments in digital infrastructure, strategic approaches to internet access optimization, and policies fostering sustainable economic growth.
Source: Scopus
