Equality of Learning Opportunity via Individual Fairness in Personalized Recommendations

TL;DR

This paper introduces a formal framework and a novel fairness metric to ensure equal learning opportunities in online educational recommendations, addressing systematic inequalities while maintaining personalization.

Contribution

It formalizes educational principles for recommendations, proposes a new fairness metric, and develops a post-processing method to balance equality and personalization in large-scale online learning platforms.

Findings

Increased fairness in recommendations with minimal personalization loss

Uncovered systematic inequalities in current educational recommender systems

Validated the effectiveness of the proposed fairness approach through experiments

Abstract

Online educational platforms are playing a primary role in mediating the success of individuals' careers. Therefore, while building overlying content recommendation services, it becomes essential to guarantee that learners are provided with equal recommended learning opportunities, according to the platform values, context, and pedagogy. Though the importance of ensuring equality of learning opportunities has been well investigated in traditional institutions, how this equality can be operationalized in online learning ecosystems through recommender systems is still under-explored. In this paper, we formalize educational principles that model recommendations' learning properties, and a novel fairness metric that combines them in order to monitor the equality of recommended learning opportunities among learners. Then, we envision a scenario wherein an educational platform should be arranged in such a way that the generated recommendations meet each principle to a certain degree for all learners, constrained to their individual preferences. Under this view, we explore the learning opportunities provided by recommender systems in a large-scale course platform, uncovering systematic inequalities. To reduce this effect, we propose a novel post-processing approach that balances personalization and equality of recommended opportunities. Experiments show that our approach leads to higher equality, with a negligible loss in personalization. Our study moves a step forward in operationalizing the ethics of human learning in recommendations, a core unit of intelligent educational systems.