Data Analytics in Higher Education: An Integrated View
Andy Nguyen, Lesley Gardner, Don Sheridan
Abstract
Data analytics in higher education provides unique opportunities to examine, understand, and model pedagogical processes. Consequently, the methodologies and processes underpinning data analytics in higher education have led to distinguishing, highly correlative terms such as Learning Analytics (LA), Academic Analytics (AA), and Educational Data Mining (EDM), where the outcome of one may become the input of another. The purpose of this paper is to offer IS educators and researchers an overview of the current status of the research and theoretical perspectives on educational data analytics. The paper proposes a set of unified definitions and an integrated framework for data analytics in higher education. By considering the framework, researchers may discover new contexts as well as areas of inquiry. As a Gestalt-like exercise, the framework (whole) and the articulation of data analytics (parts) may be useful for educational stakeholders in decision-making at the level of individual students, classes of students, the curriculum, schools, and educational systems.