A1 Journal article (refereed)
Explainable AI in Education : Techniques and Qualitative Assessment (2025)

Gunasekara, S., & Saarela, M. (2025). Explainable AI in Education : Techniques and Qualitative Assessment. Applied Sciences, 15(3), Article 1239. https://doi.org/10.3390/app15031239

JYU authors or editors

Publication details

All authors or editors: Gunasekara, Sachini; Saarela, Mirka

Journal or series: Applied Sciences

eISSN: 2076-3417

Publication year: 2025

Publication date: 25/01/2025

Volume: 15

Issue number: 3

Article number: 1239

Publisher: MDPI AG

Publication country: Switzerland

Publication language: English

DOI: https://doi.org/10.3390/app15031239

Publication open access: Openly available

Publication channel open access: Open Access channel

Publication is parallel published (JYX): https://jyx.jyu.fi/handle/123456789/99810

Abstract

Many of the articles on AI in education compare the performance and fairness of different models, but few specifically focus on quantitatively analyzing their explainability. To bridge this gap, we analyzed key evaluation metrics for two machine learning models—ANN and DT—with a focus on their performance and explainability in predicting student outcomes using the OULAD. The methodology involved evaluating the DT, an intrinsically explainable model, against the more complex ANN, which requires post hoc explainability techniques. The results show that, although the feature-based and structured decision-making process of the DT facilitates natural interpretability, it struggles to model complex data relationships, often leading to misclassification. In contrast, the ANN demonstrated higher accuracy and stability but lacked transparency. Crucially, the ANN showed great fidelity in result predictions when it used the LIME and SHAP methods. The results of the experiments verify that the ANN consistently outperformed the DT in prediction accuracy and stability, especially with the LIME method. However, improving the interpretability of ANN models remains a challenge for future research.

Keywords: artificial intelligence; stability (invariability); modelling (representation); machine learning

Free keywords: ANN; decision tree; fidelity; stability; LIME; SHAP; feature importance

Contributing organizations

Related projects

Ministry reporting: Yes

VIRTA submission year: 2025

Preliminary JUFO rating: 0