Using learning analytics to personalise the pathway

Donna M Velliaris 1

1 Independent Scholar, Singapore, Email: dvelliaris@hotmail.com

In the Higher Education (HE) sector, learning quality assurance data are typically derived from Student Experience Surveys alongside measures of attrition, progression and assessment scores. The adoption of educational technologies—such as Learning Management Systems (LMS)—has resulted in a vast set of accessible data. In reality, the work of ‘researchers’ oftentimes resides in isolation from that of ‘educators’, whereby the ‘gap’ may reflect a poor-cycle of communication and interaction between empirical studies and praxis. Data is used ‘retrospectively’ to advance future iterations of program delivery, to determine impact on learning outcomes, and to provide a benchmark on overall institutional performance. Yet, such digital footprints should be collected and analysed as a means of providing a proactive assessment of student learning and engagement. The Eynesbury Institute of Business and Technology (EIBT) is one of a growing number of private providers partnering with universities to establish pre-university pathway programs. EIBT is successfully using its data for many and varied purposes, among which includes linking available datasets with its fellow pathway colleges and partner universities in order to implement more learner-oriented services. As a second chance for prospective students who do not meet initial Australian HE entrance requirements, EIBT has an abundance of empirically-rich data or Learning Analytics (LA) that may be used to find pedagogically useful indicators, predictors and recommendations for teaching and learning advancement by careful evaluation of the findings. With analytical tools growing more powerful and their reach increasing, the aim is to assist EIBT leaders to better interpret instructor- and learner-centric data for informing future pedagogical decision-making. Objectives related to EIBT’s motivation to pursue LA include, for example: to develop a deep(er) understanding of student learning at an individual-level to support the personalisation of their educative experiences; to embed emergent feedback on student learning into practices through enabling adaptations to EIBT’s teaching and learning in a timely manner; and to identify Students-At-Risk (STAR) of poor learning experiences/outcomes, in real-time and with insight to allow for meaningful intervention i.e., to reduce the timeframe between analysis and action. As shown in this presentation, LA can explore real-time user feedback, as well as enable manipulation/visualisation based on the interests of researchers, practitioners, as well as stakeholders.

Keywords: Academic Performance, Australia, Monitoring, Pre-University Pathway, Teaching and Learning