The Effectiveness of learning analytics for identifying at-risk students in higher education
Report in the Asessement and Evaluation in Higher Education journal
Volume 45, 2020 – Issue 6: Thinking Critically About Learning Analytics, Student Outcomes and Equity of Attainment
Ed Foster and Rebecca Siddle
November 2019
Abstract
In this article Ed Foster and Rebecca Siddle investigate the effectiveness of learning analytics for identifying at-risk students in higher education institutions using data output from an in-situ learning analytics platform.
The no-engagement alerts were found to be more efficient at spotting students not progressing and not attaining than demographic data. In order to investigate the efficacy of learning analytics for addressing differential student outcomes for disadvantaged groups, the team also analysed the likelihood of students with widening participation status generating alerts compared with their non-widening participation counterparts. The odds of students with widening participation status generating an alert were on average 43% higher, demonstrating the potential of such a system to preferentially target support at disadvantaged groups without needing to target directly based on immutable factors such as their socio-economic background.
Ed Foster has worked in a variety of roles seeking to overcome barriers that prevent students from engaging effectively with learning at university. He has led the development of learning analytics at NTU since 2013, working alongside students, staff and technologists to develop the resource. Ed has conducted educational research in fields including student transition into higher education, learning development, student retention and learning analytics. He has led both national and European projects in these fields.
Dr. Rebecca Siddle works at Nottingham Trent University leading a team of researchers investigating the potential benefits of integrating learning analytics into university learning and teaching practices. She works alongside developers and her research directly influences the design of NTU’s learning analytics resource, the Student Dashboard. Her research work includes direct practical applications and also broader ethical challenges of analytics.
