Understanding mobile learning continuance after the COVID-19 pandemic: Deep learning-based dual stage partial least squares-structural equation modeling and artificial neural network analysis

Abstract

The influence of COVID-19 on educational processes has halted physical forms of teaching and learning and initiated online and mobile learning systems in most countries. The provision and usage of online and e-learning systems are becoming the main challenge for many universities during the COVID-19 pandemic. Due to the novelty of this situation, a substantial amount of research has been carried out to investigate the issue of m-learning adoption or acceptance. Nevertheless, little is known about studying to examine the continued use of m-learning, which is still in short supply and calls for further research. Five different theoretical models are integrated into this study to develop an integrated model that overcomes this limitation, including the technology acceptance model, the theory of planned behavior, the expectation-confirmation model, the Delone and McLean Information System Success Model, and the Unified Theory of Acceptance and Utilization of Technology 2. This conceptual framework shows novel relationships between variables by integrating trust, personal innovation, learning value, instructor quality, and course quality. Unlike extant literature, this study utilized a hybrid analysis methodology combining two-stage analysis using partial least squares structural equation modeling (PLS-SEM) and evolving artificial intelligence named deep learning (Artificial Neural Network [ANN]) on 250 usable responses. The sensitivity analysis results revealed that attitude has the most considerable effect on the continued use of m-learning, with 100% normalized importance, followed by perceived usefulness (88%), satisfaction (77%), and habit (61%). This research reveals that a “deep ANN architecture” may determine the non-linear relationships between variables in the theoretical model. Further theoretical and practical implications are also discussed.