Evaluating the impact of knowledge management factors on m-learning adoption: A deep learning-based hybrid sem-ann approach

This research aims to evaluate the impact of knowledge management (KM) factors, including acquisition, sharing, application, and protection on students’ behavioral intention to use m-learning. Unlike the previous m-learning empirical studies which primarily relied on structural equation modeling (SEM) analysis, this research employs an emerging hybrid analysis approach using SEM and artificial neural network (ANN) based on deep learning. This research also applies the importance-performance map analysis (IPMA) to identify the importance and performance of each factor. Through the means of an online survey, a total of 319 IT undergraduate students have participated in the study. The findings indicated that all KM factors have significant positive impacts on m-learning adoption except knowledge sharing. The analysis of both ANN and IPMA revealed that knowledge protection is the most crucial predictor of behavioral intention. Theoretically, the proposed model has provided ample explanations concerning what impacts the behavioral intention to use m-learning from the perspective of KM factors at the individual level. Practically, the results will enable decision-makers and practitioners in higher educational institutions to determine which factors should be given more importance than others and strategize their policies accordingly. Methodologically, this research ascertains the capability of the deep ANN architecture in determining the non-linear relationships among the factors in the theoretical model.