User Fairness in Recommender Systems

TL;DR

This paper highlights the importance of user fairness in recommender systems, showing that increasing diversity can inadvertently cause disparities among users, and proposes measures to quantify and address this issue.

Contribution

It introduces the concept of user fairness in recommendation systems and provides measures to quantify disparities caused by diversification algorithms.

Findings

Increased diversity leads to greater user disparity.

Post-processing for diversity can cause user discrimination.

Proposes measures to evaluate user fairness.

Abstract

Recent works in recommendation systems have focused on diversity in recommendations as an important aspect of recommendation quality. In this work we argue that the post-processing algorithms aimed at only improving diversity among recommendations lead to discrimination among the users. We introduce the notion of user fairness which has been overlooked in literature so far and propose measures to quantify it. Our experiments on two diversification algorithms show that an increase in aggregate diversity results in increased disparity among the users.