Using fair AI to predict students’ math learning outcomes in an online platform
- 28 August 2022
- journal article
- research article
- Published by Taylor & Francis in Interactive Learning Environments
- Vol. 32 (3) , 1117-1136
Abstract
As instruction shifts away from traditional approaches, online learning has grown in popularity in K-12 and higher education. Artificial intelligence (AI) and learning analytics methods such as machine learning have been used by educational scholars to support online learners on a large scale. However, the fairness of AI prediction in educational contexts has received insufficient attention, which can increase educational inequality. This study aims to fill this gap by proposing a fair logistic regression (Fair-LR) algorithm. Specifically, we developed Fair-LR and compared it with fairness-unaware AI models (Logistic Regression, Support Vector Machine, and Random Forest). We evaluated fairness with equalized odds that caters to statistical type I and II errors in predictions across demographic subgroups. The results showed that the Fair-LR could generate desirable predictive accuracy while achieving better fairness. The findings implied that the educational community could adopt a methodological shift to achieve accurate and fair AI to support learning and reduce bias.Keywords
Funding Information
- US Department of Education (R305C160004)
- University of Florida AI Catalyst (Grant -P0195022)
This publication has 65 references indexed in Scilit:
- Population validity for educational data mining models: A case study in affect detectionBritish Journal of Educational Technology, 2014
- Visualizing multi-dimensional decision boundaries in 2DData Mining and Knowledge Discovery, 2013
- Learning AnalyticsAmerican Behavioral Scientist, 2013
- Predicting Students' Progression in Higher Education by Using the Random Forest AlgorithmSystems Research and Behavioral Science, 2012
- Learning analytics and educational data mining2012
- Fairness through awareness2012
- Learning from Imbalanced Data: Evaluation Matters2012
- The teacher and the tool: instrumental orchestrations in the technology-rich mathematics classroomEducational Studies in Mathematics, 2010
- Better Bootstrap Confidence IntervalsJournal of the American Statistical Association, 1987
- Probability Inequalities for Sums of Bounded Random VariablesJournal of the American Statistical Association, 1963