Predicting the intention to use social media sites : a hybrid SEM - machine learning approach

Salloum, SA; AlAhbabi, NMN; Habes, M; Aburayya, A; Akour, I

Abstract

The study conducted aims to form a conceptual model to calculate the pupils’ acceptance of social media in education and its factors. Although the amount of research done on the acceptance of social media applications has amplified, the factors affecting its acceptance for learning are not recognized. The study is carried out by extending the Technology Acceptance Model (TAM) using perceived playfulness and social influence. Alongside this, the collected data is evaluated through Machine Learning (ML) approaches and the partial least squares-structural equation modeling (PLS-SEM). A total of 369 students enrolled at highly regarded universities in the United Arab Emirates (UAE) filled out questionnaire surveys, then analyzed, and results are stated. This research suggests that students’ intention to adopt social media networks in learning is due to significant factors such as perceived playfulness, social influence, perceived usefulness, and perceived ease of use.

Citation

Salloum, S., AlAhbabi, N., Habes, M., Aburayya, A., & Akour, I. Predicting the intention to use social media sites : a hybrid SEM - machine learning approach. Advances in Intelligent Systems and Computing, 324-334. https://doi.org/10.1007/978-3-030-69717-4_32

• Journal Article Type: Conference Paper
• Conference Name: International Conference on Advanced Machine Learning Technologies and Applications
• Conference Location: Cairo, Egypt
• End Date: Mar 22, 2021
• Online Publication Date: Mar 5, 2021
• Deposit Date: Jun 22, 2021
• Journal: Advanced Machine Learning Technologies and Applications : proceedings of AMLTA 2021
• Electronic ISSN: 2194-5365
• Publisher: Springer
• Pages: 324-334
• Series Title: Advances in Intelligent Systems and Computing
• Series Number: 1339
• Book Title: Advanced Machine Learning Technologies and Applications : proceedings of AMLTA 2021
• ISBN: 9783030697167-(print);-9783030697174-(ebook)
• DOI: https://doi.org/10.1007/978-3-030-69717-4_32
• Publisher URL: https://doi.org/10.1007/978-3-030-69717-4_32
• Related Public URLs: https://doi.org/10.1007/978-3-030-69717-4
• Additional Information: Event Type : Conference