New Discoveries for User Acceptance of E-Learning Analytics Recommender Systems in Saudi Arabia

New Discoveries for User Acceptance of E-Learning Analytics Recommender Systems in Saudi Arabia

Hadeel Alharbi (University of New England, Armidale, Australia) and Kamaljeet Sandhu (University of New England, Armidale, Australia)
Copyright: © 2019 |Pages: 12
DOI: 10.4018/IJIDE.2019010103
OnDemand PDF Download:
No Current Special Offers


This article adopts e-learning analytics principles to provide a new model to explain the acceptance behaviour of recommender systems adoption with e-learning in the Saudi Arabian context and reflects the increasing focus of the Saudi Arabian Ministry of Education on delivering online educational services. This focus has come at the necessity to improve overall access to the education system, and higher education and has been driven with evidence of improving learning outcomes with electronic learning (e-learning) information and instructional technology with the use of e-learning analytics recommender systems. This review utilises the technology acceptance model as a theoretical framework to generate a set of interlocked hypotheses that go to explaining student behaviours towards technological acceptance and continued usage intention of recommender systems.
Article Preview


The successful integration of face-to-face learning with e-learning systems is determined by the level of technological acceptance and continuity of use by users within the learning environment. One of the differences and challenges that e-learning environments face is the dynamic shift towards changing content offered by e-learning systems compared to the more ridged and inflexible course materials offered in face-to-face learning. The ability to moderate content in real time to meet the demands of the student makes e-learning systems increasingly more valuable as a teaching tool, particularly for those who need special learning assistance (Al-Shehri, 2010). However, one of the current limitations in Saudi Arabia to the effective role out of e-learning systems is user satisfaction and its relationship to the speed of the internet and related services (Xanthidis, 2016). It is anticipated there will be increased focus on non-traditional learning systems across all levels of the Saudi education sector as the quality and penetration of the internet deepens in the Kingdom, and this will further lead to an increased level of acceptance and understanding of e-learning systems.

Notwithstanding the shift in Saudi education policy towards the introduction of e-learning systems, particularly after 2006, the implementation of e-learning systems has experienced many challenges (Al-Shehri, 2010). Al-Shehri (2010) noted that the lack of user familiarity with e-learning systems resulted in up to 50% of all users failing to take advantage of the full range of services offered by the e-learning system. This implies a failing in the methodological approach to the introduction of the new technology. More importantly, it highlights a lack of engagement in how the technology is to be used and the explanation of its benefits to users as they become more confident with the system over time. Therefore, understanding the conditions that lead to greater acceptance of e-learning analytics recommender systems is critical to increasing e-learning instruction use given that three-quarters of all students prefer non-e-learning modes of instruction (Ubbisa, 2014).

Learning analytics involves data analysis to guide decision making in education systems (Czerkawski, 2014). Central to the decision-making outcomes is the approach to leverage student data for the delivery of more personalised and adaptive teaching and learning (Miteva, Stefanov, & Stefanova, 2016). In terms of process, a statistical analysis of student data is undertaken to develop a deeper level of understanding of the student experience. The results of the data analysis are then used to inform strategies to provide more individualised instruction to meet each student’s unique learning needs (Miteva et al., 2016). All university learning management systems (LMS) have reporting metrics (e.g. time of access, time spent on pages, number of posts) embedded within them. Moreover, dashboard software for LMS is available to collect key learner metrics and to aggregate data (West, 2012). However, learning analytics provides a more sophisticated data set in relation to students’ online behaviours.

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 13: 4 Issues (2022): Forthcoming, Available for Pre-Order
Volume 12: 4 Issues (2021): 3 Released, 1 Forthcoming
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
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