Modeling Students' Performances in Activity-Based E-Learning From a Learning Analytics Perspective

Abstract

This paper reports the findings of a research using marks of students in learning activities of an online module to build a predictive model of performance for the final assessment of the module. The objectives were (1) to compare the performances of students of two cohorts in terms of continuous learning assessment marks and final learning activity marks and (2) to model their final performances from their learning activities forming the continuous assessment using predictive analytics and regression analysis. The findings of this study combined with other findings as reported in the literature demonstrate that the learning design is an important factor to consider with respect to application of learning analytics to improve teaching interventions and students' experiences. Furthermore, to maximise the efficiency of learning analytics in eLearning environments, there is a need to review the way offline activities are to be pedagogically conceived so as to ensure that the engagement of the learner throughout the duration of the activity is effectively monitored.

Learner satisfaction, engagement and performances in an online module: Implications for institutional e-learning policy

“…The module focused on the learning-bydoing approach, through authentic assignments such as developing a website, use an authoring tool, engage in critical reflection through blogging and YouTube video posts, general forum discussions as well as drill and practice questions such as online MCQs. The learning design principle that guided the pedagogical approach was the knowledge acquisition, application and construction cycle through sharing & reflective practice (Rajabalee et al 2020). Although the module was fully online, it is necessary to point out, that not all of the learning activities necessitated persistent online presence for completion.…”

“…The proposition is that being active online through logins, active sessions and clicks actually reflects actual engagement in an online course and result in better student performances. However, this model mainly works in classic online modules, and there is limited availability of literature measuring students' engagement in activity-based hybrid learning environments where there is a mix online and offline activities (Rajabalee et al 2020).…”

Improving pedagogical design in higher education: untangling the learning activity complexity through students’ declared performance

“…Therefore, using a semi-automatised approach, such as VNA, to look into the qualitative data would become a midway tactic to enrich the course evaluation's perspectives using the benefits of automatic analysis (Rajabalee et al, 2020) but avoiding the most simplistic approaches of learning analytics based on clicks. Therefore, it would also take other procedures closer to the social learning analytics proposals (Buckingham Shum et al, 2016;Buckingham-Shum & Ferguson, 2012) and critical learning analytics' approaches (Scott & Nichols, 2017).…”

“…Due to the above, many of the studies that aim to analyse a course's performanceor the adequacy of its learning designalmost always, just compare aspects of the design with results or with final satisfaction rates. Lately, especially in higher education, these comparisons have been "enhanced" with discrete data about single aspects of the students' activity generally collected with a specific instrument orat bestwith a repeated measurement (and some learning analytics) (Mangaroska & Giannakos, 2019;Pishtari et al, 2020;Rajabalee et al, 2020). Due to this effort to avoid the complexity, these studies' results assume a black box in developing the learning activity, and their conclusions are aligned with what Biesta (2010) called an input-output vision between pedagogies (way of teaching) and learning results.…”

Effect of Activity-Based Teaching on Student Achievement at Elementary Level

“…This condition leads to rote learning without thorough knowledge of scientific concepts, phenomena, and theories (Zhou & Luh, 2021). Researchers believe that if a teacher has few resources, they must use the traditional lecture technique (Rajabalee, Santally, & Rennie, 2020). Boostrom (1991) states that more capable teachers who can embrace lecture style cannot be expected to follow activity-oriented education so quickly.…”