PLS Model Performance for Factors Influencing Student Acceptance of E-Learning Analytics Recommender

PLS Model Performance for Factors Influencing Student Acceptance of E-Learning Analytics Recommender

Kamaljeet Sandhu (University of New England, Armidale, Australia) and Hadeel Alharbi (University of New England, Armidale, Australia)
DOI: 10.4018/IJVPLE.2020070101

Abstract

The aim of this article is to present the multivariate analyses results of the factors that influence students' acceptance and the continuance usage intention of e-learning analytics recommender systems in higher education institutions in Saudi Arabia. Data was collected from 353 Saudi Arabian university students via an online survey questionnaire. The research model was then used to examine the hypothesised relationships between user experiences of an e-learning analytics recommender system and their intentions for long-term adoption of the system. The research model was primarily based on the Technology Acceptance Model (TAM) developed by Davis (1989) – the variables ‘perceived usefulness,' ‘perceived ease of use,' and ‘acceptance,' particularly – with ‘continuance usage intention' added as an endogenous construct, and with ‘service quality' and ‘user experience' added as external variables.
Article Preview
Top

2. Research Model And Hypotheses

The research model to investigate the factors affecting students' acceptance and the continuance usage intention of e-learning analytics recommender systems is primarily based on the TAM developed by Davis (1988). It incorporates ‘service quality’ and ‘user experience’ as external variables; and includes the TAM variables: ‘perceived usefulness,’ ‘perceived ease of use,’ and ‘acceptance’. The research model also extended the TAM by adding ‘continuance usage intention’ as the ultimate endogenous construct in the developed model (see Figure 1).

Figure 1.

Research model of e-learning analytics recommender system acceptance

IJVPLE.2020070101.f01

Following analysis of the findings reported in previous studies (e.g. DeLone and McLean, 1992; Gorla et al., 2010; Rana et al., 2015) and in consideration of the key issues explored in the literature (e.g. Dağhan, and Akkoyunlu, 2016; Karapanos, 2013; Lee, 2010; Lin 2011), the following hypotheses were formulated:

  • H1: The perceived recommender system usefulness affects e-learning analytics recommender system acceptance.

  • H2: The perceived recommender system ease of use affects e-learning analytics recommender system acceptance.

  • H3: The e-learning analytics recommender system acceptance affects the continuity use of recommender system.

  • H4: The e-learning analytics recommender system service quality affects perceived recommender system ease of use.

  • H5: The e-learning analytics recommender system user experience affects perceived recommender system usefulness.

Complete Article List

Search this Journal:
Reset
Open Access Articles
Volume 11: 2 Issues (2021): Forthcoming, Available for Pre-Order
Volume 10: 2 Issues (2020)
Volume 9: 2 Issues (2019)
Volume 8: 2 Issues (2018)
Volume 7: 2 Issues (2017)
Volume 6: 1 Issue (2016)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing