From Students Struggles to Teachers Insights
A Dashboard of Student-AI Interactions in ML Practical Assignments
Boyun Zhang (Student TU Delft)
Ilinca Rentea (TU Delft - Electrical Engineering, Mathematics and Computer Science)
Gosia Migut (TU Delft - Electrical Engineering, Mathematics and Computer Science)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
When students work on self-paced, unsupervised practical assignments in Machine Learning courses, teachers have little visibility into the difficulties students encounter. In our Machine Learning course, students completed a practical assignment using JELAI, an AI-supported programming environment. The recorded student-AI interactions were classified into pedagogically meaningful categories and visualized in a teacher-facing dashboard. An initial evaluation showed that teachers found the dashboard useful, while also identifying areas for improvement. We describe our experience and discuss the potential and challenges of using student-AI interactions to improve teaching practice.
help_outline