Equality of Learning Opportunity via Individual Fairness in Personalized Recommendations

Abstract

Online education platforms play an increasingly important 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 principles, 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 shape a blueprint of the decisions and processes to be considered in the context of equality of recommended learning opportunities, based on principles that need to be empirically-validated (no evaluation with live learners has been performed). To this end, we first provide a formalization of educational principles that model recommendations’ learning properties, and a novel fairness metric that combines them 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 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. This paper provides a theoretical foundation for future studies of learners’ preferences and limits concerning the equality of recommended learning opportunities.

RAWLSNET: Altering Bayesian Networks to Encode Rawlsian Fair Equality of Opportunity

“…There has also been significant interest in complementary projects in the algorithmic fairness literature which appeal to substantive equality of opportunity principles, including FEO (Hardt, Price, and Srebro 2016;Dwork et al 2012;Joseph et al 2016;Marras et al 2020;Zhang and Bareinboim 2018;Kang et al 2020;Friedler, Scheidegger, and Venkatasubramanian 2016). These appeals are used to justify various specific fairness metrics, and to adjudicate disputes between these metrics.…”

Consumer Fairness in Recommender Systems: Contextualizing Definitions and Mitigations

“…Recommender systems help us make decisions, from selecting books to choosing friends [24]. Their wide adoption has spurred investigations into possibly unfair practices in the systems' mechanisms [9,12,11,21,5]. Fairness is a concept of nondiscrimination on the basis of the membership to protected groups, identified by a protected feature, e.g., gender and age in anti-discrimination legislation 1 .…”

Robust Reputation Independence in Ranking Systems for Multiple Sensitive Attributes

“…Given their role in our experience online, the results they produce must not harm users in any way. However, it is known that a biased ranking can lead to a loss of trust in the system (Pan et al, 2007), and that a ranking can also hide a discrimination against users belonging to legally-protected classes (Ekstrand et al, 2019;Boratto et al, 2021;Marras et al, 2021).…”