ARTIFICIAL NEURAL NETWORK APPROACH TO PREDICT LMS ACCEPTANCE OF VOCATIONAL SCHOOL STUDENTS


Creative Commons License

Ozkan U. B., Cigdem H., Erdoğan T.

TURKISH ONLINE JOURNAL OF DISTANCE EDUCATION, vol.21, no.3, pp.156-169, 2020 (ESCI) identifier identifier

  • Publication Type: Article / Article
  • Volume: 21 Issue: 3
  • Publication Date: 2020
  • Doi Number: 10.17718/tojde.762045
  • Journal Name: TURKISH ONLINE JOURNAL OF DISTANCE EDUCATION
  • Journal Indexes: Emerging Sources Citation Index (ESCI), Scopus, EBSCO Education Source, ERIC (Education Resources Information Center), Index Islamicus, Directory of Open Access Journals
  • Page Numbers: pp.156-169
  • Keywords: Artificial neural networks, LMS acceptance, UTAUT, MOODLE, social influence, vocational school, USER ACCEPTANCE, INFORMATION-TECHNOLOGY, SYSTEMS, MODEL
  • TED University Affiliated: Yes

Abstract

The contribution of e-learning technologies, especially LMS which has become an important component of e-learning, is significantly increasing in higher education. It is critical to understand the factors that affect the behavioral intention of students towards LMS use. The aim of this study is to explore predictors of students' acceptance of Course Portal at a postsecondary vocational school level. We utilised a framework suggested by Sezer and Yilmaz (2019) for understanding students' acceptance of LMS. This framework obtains the main constructs in UTAUT: namely, performance expectancy, effort expectancy, social influence and facilitating conditions. More external variables, associate degree programs, high school type, academic grade point average were also adopted. Accordingly, 387 students were answered the questionnaire for investigating behavioral intention. Artificial neural network analysis (ANN) was used to predict students' acceptance of LMS use according to variables associated with their use of LMS technology. ANN analyses in the present study revealed that performance expectancy, effort expectancy, social influence and facilitating conditions are important predictors of students' behavioral intention to use LMS. Nevertheless, performance expectancy was found to be the most influencing predictor of LMS use. The analyses of this research provides evidence on the utilization of ANN to predict the determining factors of LMS acceptance.