What drives the adoption of mobile learning services among college students: An application of SEM-neural network modeling

•Examined the factors related to user adoption of mobile learning services.•We proposed an integrated model combined UTAUT and the Delone and Mclean ISS model.•An SEM-Neural Network approach was adopted in this study.•IQ, habit, SQ, HM, FC, and SI, positively influenced the adoption of m-learning.•PV, EE, PE, and privacy were not significant predictors of BI.•The significant factors explained 70 % of the variance toward based on SEM results. This research aimed at examining factors influencing college students to adopt mobile learning (m-learning) services. An integrated model combined the information systems success (ISS) and Unified Theory of Acceptance and Use of Technology (UTAUT2), was developed to identify m-learning determinants. A sample of 552 was recruited to test hypotheses using structural equation modeling (SEM). The significant factors explained 70 % of the variance toward Behavioral Intention (BI) based on SEM results. While price value (PV), effort expectancy (EE), performance expectancy (PE), and privacy (PR) were not significant predictors of BI, the results of the neural network model ranked the predictive power of the factors in the following order: information quality, habit (HB), system quality (SYQ), hedonic motivation (HM), facilitating condition (FC), and social influence (SI), positively influenced m-learning adoption. The findings of this study helps the policy makers at higher educational institutions to formulate strategies to enhance students’ learning experience in upcoming crises and place a focus on sustainable mobile learning environment.