Student Centred Design of a Learning Analytics System
Researchers from Keele University have developed a novel approach to Learning Analytics - by putting students at the heart of the design.
Current Learning Analytics (LA) systems are primarily designed with University staff members in mind, with very few being aimed at students, and almost none being developed with direct student involvement and evaluation.
Led by Dr Ed de Quincey, the Keele University team designed an LA system focused on the student’s perspective, including personalised content and allowing students to choose how they wanted to interact with the system. Their research was recently presented at the Learning Analytics and Knowledge Conference 2019.
Dr Ed de Quincey, Senior Lecturer in the School of Computing and Mathematics at Keele University explains:
“One of the major gaps in Learning Analytics is that there aren’t many systems that make learning related data available to the people that probably need it the most; students. There is huge potential though in giving students access to their own data and using it to provide recommendations that improve their engagement or reinforce positive learning behaviour and achievement.”
The new LA system uses a novel approach to understand the reasons why students want to study at university, and maps their engagement and predicted outcomes to these motivations, with weekly personalised notifications and feedback. Students are also given the choice of how to visualise the data either via a chart-based view or to be represented as themselves.
The research, which was funded by a HEFCE Catalyst Award, employed a variety of methods to engage students in the design, development and evaluation of a student-facing LA dashboard.
The LA system was integrated into the delivery of four undergraduate modules, with 169 student sign-ups. Students were mostly positive about the usability and interface design of the system, and the majority of students could see how the LA system could support their learning to improve their grades, and said that it would influence their behaviour. In some cases, this has had a direct impact on their levels of engagement.
Dr Ed de Quincey comments:
“Our tool not only aggregates data from sources such as attendance and Virtual Learning Environment and Lecture Capture usage, but also then gives predicted scores and specific recommendations to students each week e.g. to improve attendance at practicals, based on machine learning models that we have created. This has shown to improve levels of online engagement as well as improving attendance. We believe that including students in the design and development of the systems that support their learning can have significant benefits, but it is something that is being neglected in the sector.”
Following from this work, Dr Ed de Quincey will be leading a project to embed Learning Analytics into programme review and curriculum design at Keele University. The project will look at aggregating learning data from a variety of sources, including student feedback, KLE usage, and attendance, and look at how they can be integrated into the annual module and programme review process - following a user-centred design approach. Find out more about the project.
About the research:
Ed de Quincey, Chris Briggs, Theocharis Kyriacou, and Richard Waller. 2019. Student Centred Design of a Learning Analytics System. In Proceedings of International Conference on Learning Analytics and Knowledge (LAK’19). ACM, New York, NY, USA, 10 pages.