What is it about?
Students at university who struggle in some courses often do not seek help to the educational teams. Teachers want to minimize the number of students who dropout of their courses because of difficulties. Research tries to automatically detect these students who struggle such that teachers can intervene before these students decide to dropout. Our paper highlights one issue in a methodology often employed when doing such research.
Featured Image
Why is it important?
Our work could prevent numerous issues at the moment we decide to deploy dropout detection applications live in classroom settings.
Perspectives
Read the Original
This page is a summary of: Methodological Considerations for Predicting At-risk Students, February 2022, ACM (Association for Computing Machinery),
DOI: 10.1145/3511861.3511873.
You can read the full text:
Contributors
The following have contributed to this page