Orientation: Case studies in learning analytics

Context:
Computer Science School at an Australian university; the two largest programmes are the graduate Data Science programme and the undergraduate Computer Science programme.
Objective:
The objective is to examine the alignment of instructors’ feedback practices in real educational settings with well-established theories of learner-centered feedback, while analysing differences between two large datasets (undergraduate and graduate programmes).
Data:
Data on feedback provided through the LMS (2022): a total of 95 courses across all years of study, involving 4,959 students and approximately 200 instructors. The selected programmes represented the largest student populations at each level of study, with 2,187 graduate and 2,772 undergraduate students. Ten percent of the feedback from each course was analysed, amounting to 16,408 sentences.
Analysis:
Descriptive and inferential statistics; Ordered Network Analysis (implemented in R).
Results:
The study shows that feedback practices in higher education, as analysed within the selected study programmes, are partially aligned with the learner-centered feedback model, with a pronounced focus on the sensemaking dimension. However, significant differences were observed in the other two dimensions — future impact and agency — indicating different approaches depending on the level of education. At the graduate level, future impact is prioritised, with guidance for advanced tasks. At the undergraduate level, greater emphasis is placed on fostering agency through student engagement and participation. The study also shows that feedback practices differ according to levels of student achievement.
Full study:
Aldino, A. A.; Tsai, Y.-S.; Gupte, S.; Henderson, M.; Nath, D.; Gašević, D.; Chen, G. (2025).
Analytics of Learner-Centered Feedback: A Large-Scale Case Study in Higher Education . Computers & Education, 237, 105360.