Tutorial on Economic Perspectives on Fairness in Information Retrieval

Recently, fairness-aware information retrieval (IR) systems have been receiving much attention. Numerous fairness metrics and algorithms have been proposed. The complexity of fairness and IR systems makes it challenging to provide a systematic summary of the progress that has been made. This complexity calls for a more structured framework to navigate future fairness-aware IR research directions. The field of economics has long explored fairness, offering a strong theoretical and empirical foundation. Its system-oriented perspective enables the integration of IR fairness into a broader framework that considers societal and intertemporal trade-offs. In this tutorial, we first highlight that IR systems can be understood as a specialized economic market. Then, we re-organize fairness algorithms through three key economic dimensions-macro vs.\ micro, demand vs.\ supply, and short-term vs.\ long-term. We effectively view most fairness categories in IR from an economic perspective. Finally, we illustrate how this economic framework can be applied to various real-world IR applications and we demonstrate its benefits in industrial scenarios. Different from oth fairness-aware tutorials, our tutorial not only provides a new and clear perspective to re-frame fairness-aware IR but also inspires the use of economic tools to solve fairness problems in IR. We hope this tutorial provides a fresh, broad perspective on fairness in IR, highlighting open problems and future research directions.

Website: https://economic-fairness-ir.github.io/