A Good Classifier is Not Enough: A XAI Approach for Urgent Instructor-Intervention Models in MOOCs

Alrajhi, Laila; Pereira, Filipe Dwan; Cristea, Alexandra I.; Aljohani, Tahani

Abstract

Deciding upon instructor intervention based on learners’ comments that need an urgent response in MOOC environments is a known challenge. The best solutions proposed used automatic machine learning (ML) models to predict the urgency. These are ‘black-box’-es, with results opaque to humans. EXplainable artificial intelligence (XAI) is aiming to understand these, to enhance trust in artificial intelligence (AI)-based decision-making. We propose to apply XAI techniques to interpret a MOOC intervention model, by analysing learner comments. We show how pairing a good predictor with XAI results and especially colour-coded visualisation could be used to support instructors making decisions on urgent intervention.

Citation

Alrajhi, L., Pereira, F. D., Cristea, A. I., & Aljohani, T. (2022). A Good Classifier is Not Enough: A XAI Approach for Urgent Instructor-Intervention Models in MOOCs. In M. Mercedes Rodrigo, N. Matsuda, A. I. Cristea, & V. Dimitrova (Eds.), Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners’ and Doctoral Consortium (424-427). Springer Verlag. https://doi.org/10.1007/978-3-031-11647-6_84

• Online Publication Date: Jul 26, 2022
• Publication Date: 2022
• Deposit Date: Sep 26, 2022
• Publicly Available Date: Jul 27, 2023
• Publisher: Springer Verlag
• Pages: 424-427
• Series Title: Lecture Notes in Computer Science
• Series Number: 13356
• Book Title: Artificial Intelligence in Education. Posters and Late Breaking Results, Workshops and Tutorials, Industry and Innovation Tracks, Practitioners’ and Doctoral Consortium
• ISBN: 978-3-031-11646-9
• DOI: https://doi.org/10.1007/978-3-031-11647-6_84
• Public URL: https://durham-repository.worktribe.com/output/1620668