Title: Understanding mobile learning continuance from an online-cum-offline learning perspective: a SEM-neural network method

Authors: Miao Zhang; Yuangao Chen; Shuai Zhang; Wenyu Zhang; Yixiao Li; Shuiqing Yang

Addresses: School of Education Science and Technology, Zhejiang University of Technology, Hangzhou, 310014, China ' School of Information Management and Artificial Intelligence, Zhejiang University of Finance and Economics, No. 18, XueYuan Street, XiaSha Higher Education Zone, Hangzhou City 310018, China ' School of Information Management and Artificial Intelligence, Zhejiang University of Finance and Economics, No. 18, XueYuan Street, XiaSha Higher Education Zone, Hangzhou City 310018, China ' School of Information Management and Artificial Intelligence, Zhejiang University of Finance and Economics, No. 18, XueYuan Street, XiaSha Higher Education Zone, Hangzhou City 310018, China ' School of Information Management and Artificial Intelligence, Zhejiang University of Finance and Economics, No. 18, XueYuan Street, XiaSha Higher Education Zone, Hangzhou City 310018, China ' School of Information Management and Artificial Intelligence, Zhejiang University of Finance and Economics, No. 18, XueYuan Street, XiaSha Higher Education Zone, Hangzhou City 310018, China

Abstract: Based on uses, gratifications theory and literature related to perceived integration, this study investigated the factors that influence college students' mobile learning continuance from an online-cum-offline learning perspective. A research model was developed and tested against data collected from 261 college students who are the mobile learning users of an online flipped learning platform in China. A multi-analytic method was employed whereby the proposed model was first tested using structural equation modelling (SEM), and the results of the SEM were used as inputs for a neural network approach to explain mobile learning continuance. The results show that perceived integration affects mobile learning continuance directly and indirectly via students' extrinsic gratification (social need) and intrinsic gratifications (affective need and entertainment need). According to the normalised importance, affective need is the most significant factor affecting mobile learning continuance, following by social need and entertainment need.

Keywords: mobile learning; perceived integration; gratifications; neural network; multi-analytic method.

DOI: 10.1504/IJMC.2022.119995

International Journal of Mobile Communications, 2022 Vol.20 No.1, pp.105 - 127

Received: 11 Apr 2019
Accepted: 09 Jul 2020
Published online: 04 Jan 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article