Predicting the drivers of behavioral intention to use mobile learning: A hybrid SEM-Neural Networks approach

• We examined the determinants of mobile learning using a hybrid SEM–ANN approach.
• TAM has significant influence on the intention to adopt.
• Psychological science constructs are non-significant with the intention to adopt.
• The moderating effect of age and gender are non-significant in this study.
• The model is able to explain 53.4% of the variance with effect size of 0.399.

This study empirically investigates on the elements that affect the user’s intention to adopt mobile learning (m-learning) using a hybrid Structural Equation Modeling–Artificial Neural Networks (SEM–ANN) approach. A feed-forward-back-propagation multi-layer perceptron ANN with the significant determinants from SEM as the input units and the Root Mean Square of Errors (RMSE) indicated that the ANN achieved high prediction accuracy. All determinants are relevant and their normalized importance was examined through sensitivity analysis. The explanation on new computer technologies acceptance have been primarily based on the Technology Acceptance Model (TAM). Since TAM omits the psychological science constructs, the study address the weaknesses by incorporating two additional constructs, namely the personal innovativeness in information technology (PIIT) and social influences (SI). Out of the 400 survey distributed to mobile users, 216 usable questionnaires were returned. The results uncovered that the intention to adopt m-learning has significant relationship with TAM. The findings for PIIT, SI and the control variables of age, gender and academic qualifications however show mixed results. The results provide valuable information for mobile manufacturers, service providers, educational institutions and governments when strategizing their adoption strategies. Additionally, from the perspective of an emerging market, the study has successfully extended TAM with psychological constructs.