Combining event- and variable-centred approaches to institution-facing learning analytics at the unit of study level

Abstract

Purpose - The paper demonstrates the utility of combining event-centred and variable-centred approaches when analysing big data for higher education institutions. It uses a large, university-wide dataset to demonstrate the methodology for this analysis by case study. It presents empirical findings about relationships between student behaviours in a learning management system and the learning outcomes of students, and further explores these findings using process modelling techniques. Design/methodology/approach - The paper describes a two-year study in a Chilean university, using big data from a learning management system and from the central university database of student results and demographics. Descriptive statistics of LMS use in different years presents an overall picture of student use of the system. Process mining is described as an event-centred approach to give a deeper level of understanding of these findings. Findings - The study found evidence to support the idea that instructors do not strongly influence student use of an LMS. It replicates existing studies to show that higher performing students use an LMS differently to lower performing students. Research limitations/implications - The study is limited by its institutional context, its two-year time frame, and its exploratory mode of investigation to create a case study. Practical implications - The paper is useful for institutions in developing methodology for using big data from a learning management system to make use of event-centred approaches. Originality/value - The paper is valuable in replicating and extending recent studies using event-centred approaches to analysis of learning data. The study here is a larger scale than existing studies (using a university-wide dataset), in a novel context (Latin America), that provides a clear description for how and why the methodology should inform institutional approaches.