Joint Multisided Exposure Fairness for Recommendation
This work addresses fairness concerns in recommendation systems for stakeholders like marginalized groups and content producers, but it is incremental as it builds on prior metrics.
The paper tackles the problem of systemic exposure disparities in recommender systems, where groups of items may be under- or over-exposed to groups of users, leading to social harms like allocative or representational harm. It extends an existing framework to formalize joint exposure fairness metrics for both consumers and producers, and demonstrates optimization of ranking policies to address these biases.
Prior research on exposure fairness in the context of recommender systems has focused mostly on disparities in the exposure of individual or groups of items to individual users of the system. The problem of how individual or groups of items may be systemically under or over exposed to groups of users, or even all users, has received relatively less attention. However, such systemic disparities in information exposure can result in observable social harms, such as withholding economic opportunities from historically marginalized groups (allocative harm) or amplifying gendered and racialized stereotypes (representational harm). Previously, Diaz et al. developed the expected exposure metric -- that incorporates existing user browsing models that have previously been developed for information retrieval -- to study fairness of content exposure to individual users. We extend their proposed framework to formalize a family of exposure fairness metrics that model the problem jointly from the perspective of both the consumers and producers. Specifically, we consider group attributes for both types of stakeholders to identify and mitigate fairness concerns that go beyond individual users and items towards more systemic biases in recommendation. Furthermore, we study and discuss the relationships between the different exposure fairness dimensions proposed in this paper, as well as demonstrate how stochastic ranking policies can be optimized towards said fairness goals.