LAK 2026: "Detect, Explain, Act: How Teachers Trust and Use an Explainable Real-Time Monitoring Dashboard to Detect Student Outliers in Class"

This paper for the LAK 2026 conference is an outcome of the master's thesis by Anissa Faik, which I guided and Katrien Verbert supervised. We created a dashboard for teachers to monitor students' performance on an e-learning platform in real-time. We studied how explanations influence teachers' trust in an algorithm that detects outlier students. We found that teachers successfully integrated the dashboard into their classes, and that their trust was shaped by many factors. Crucially, the data-centric explanations enabled teachers to validate the accuracy of outlier predictions, check alignment with their prior knowledge of students, and identify suitable interventions.

Paper

Read the full paper on the ACM Digital Library.

Presentation

Demo