What the study found
The authors present a public, de-identified clickstream dataset from two first-year bachelor courses at KU Leuven collected over three academic years. They also provide transparent documentation of how the data were de-identified and report privacy and utility validation results.
Why the authors say this matters
The study suggests that open and transparent datasets can support the development and evaluation of learning analytics, while addressing concerns about the sensitive and personal nature of learning data. The authors also say such availability can support transfer of findings across domains and collaboration on joint educational initiatives.
What the researchers tested
The researchers assembled a detailed clickstream dataset from learner interactions with digital study materials and learning tools in two first-year bachelor courses across three academic years. They accompanied the public dataset with documentation of the de-identification process and evaluated privacy and utility.
What worked and what didn't
The abstract states that the dataset is public and that the authors report privacy and utility validation results. It does not specify in the abstract which validation outcomes were successful or which, if any, were problematic.
What to keep in mind
The abstract does not describe the detailed validation results, so the specific privacy and utility findings are not available here. It also does not state broader limitations beyond the general ethical and privacy concerns associated with learning data.
Key points
- A public, de-identified clickstream dataset was released for learning analytics.
- The dataset comes from two first-year bachelor courses at KU Leuven and spans three academic years.
- The authors provide documentation of the de-identification process.
- Privacy and utility validation results are reported, but the abstract does not describe them in detail.
- The authors say open datasets can support learning analytics development, evaluation, and collaboration.
Disclosure
- Research title:
- De-identified student activity dataset released for learning analytics
- Authors:
- Elena Tiukhova, Dimitri Van Landuyt, Bart Baesens, Monique Snoeck
- Institutions:
- KU Leuven, University of Southampton
- Publication date:
- 2026-02-27
- OpenAlex record:
- View
Get the weekly research newsletter
Stay current with peer-reviewed research without reading academic papers — one filtered digest, every Friday.