A Smart Learning Environment for a Blended Experience

Introduction

The proliferation of online courses is testament to the increased demand and rising awareness of education, as the widespread pervasiveness of information technology in all sectors of our society paved the way for educational institutions to easily and conveniently have access to a wider audience. The effectiveness of e-learning courses has been shown over the years (Haq et al., 2018; Russell, 2001) that there exists no significant difference in learning outcomes when compared to the traditional mode of delivery. However, the distinction between good and bad e-learning has also been outlined by a number of studies (Al-Mahmood & McLoughlin, 2004; Connell, 2009; Zou, 2006), and reported to be no different from the poor and inadequate use of any other medium as a teaching platform. The early e-learning stages focused mainly on transferring face-to-face classes and the familiarization of the instructors with underlying technology which it heavily depends on, and thereby characteristic inefficiencies as well as optimal engagement of the electronic medium tend to be much more dominant, influential, and explicitly discernible. The popularity of e-learning courses and the onset of Massive Open Online Courses (MOOCs) brought about additional issues related to assessment (Admiraal et al., 2015), critical thinking (Akyüz & Samsa, 2009), and a sense of isolation and detachment (Camilleri et al., 2013). As a result, the next stage of online learning witnessed a shift in the attention of educators and e-learning specialists from transfer of knowledge to knowledge building and management, seeking to enhance innovative approaches while redefining better processes of learning. This is the case with our smart Virtual Learning Environment (VLE), called Scholar, we have taken full advantage of new e-learning affordances (Cope & Kalantzis, 2017) to pedagogically design and develop it based on a reflexive ideology whereby complex reasoning skills such as critical and creative thinking form part of the process. Additionally, Computer Science collaborators employed available learning analytics and data mining techniques to automate critical thinking assessment through topic modelling (Kuzi et al., 2018; Zhai, 2008), as well as semantically analyzing text to assess peer reviews (Zhai et al., 2004) (Shubhra-Kanti et al., 2018). The purpose of this chapter is to report on the work done to extend both these lines of research and to document results from an empirical study in the form of in-class experiences in an attempt to address student needs in the next stage of online learning whereby the benefits of personalization are employed at different levels and granularity thereby relieving not only students’ sense of isolation and detachment, but also optimizing the learning process through real-time learning data-mining and analytics. This will lead us to provide insights and recommendations to two basic research questions, namely:

• 1.

  How might we productively use machine learning techniques to support the student throughout the online learning process?

• 2.

  Do the machine-supported and machine-mediated automated processes improve learning outcomes over and above the existent capabilities and functionalities offered by the latest e-learning portals?