FairnessBiasTransparencycs.AI
Towards Responsible AI in Education: Hybrid Recommendation System for K-12 Students Case Study
Nazarii Drushchak, Vladyslava Tyshchenko, Nataliya Polyakovska
February 27, 2025
2025 IEEE/ACM International Workshop on Responsible AI Engineering (RAIE)
5 citations
1 influential
Key Takeaways
-
Personalization in education comes with hidden risks: AI recommendation systems in schools can unintentionally introduce biases that limit fair access to learning resources, even when designed with good intentions to personalize student experiences.
-
Technical solutions exist for fairness: The study demonstrates that combining graph-based modeling with bias detection frameworks can help identify and reduce disparities across different student groups, suggesting that responsible AI design is achievable in educational settings.
-
Continuous monitoring is essential: Rather than a one-time fix, the research emphasizes that educational AI systems require ongoing monitoring to maintain equitable access to extracurricular activities, learning resources, and volunteering opportunities for all K-12 students.
-
Transparency and equity must be built in from the start: The framework addresses fairness concerns by analyzing feedback across protected student groups, indicating that responsible AI requires intentional design choices that prioritize transparency and equal treatment alongside personalization.
Abstract
The growth of Educational Technology (EdTech) has enabled highly personalized learning experiences through Artificial Intelligence (AI)-based recommendation systems tailored to each student needs. However, these systems can unintentionally introduce biases, potentially limiting fair access to learning resources. This study presents a recommendation system for K-12 students, combining graph-based modeling and matrix factorization to provide personalized suggestions for extracurricular activities, learning resources, and volunteering opportunities. To address fairness concerns, the system includes a framework to detect and reduce biases by analyzing feedback across protected student groups. This work highlights the need for continuous monitoring in educational recommendation systems to support equitable, transparent, and effective learning opportunities for all students.