Reputation Equity in Ranking Systems

Ramos, Guilherme;Boratto, Ludovico;Marras, Mirko

2021-01-01

---

Abstract

The impact of ranking systems on humans is an aspect that is getting a lot of attention. In this paper, we consider a class of algorithms, known as reputation-based ranking systems, which rank the items based on a reputation score automatically computed for each user. Recent literature introduced the concept of reputation independence, which considers a sensitive attribute of the users (such as gender or age) and makes the reputation scores independent from that attribute. Here, we show that if we consider a different sensitive attribute w.r.t. a user to introduce independence, reputation scores are still biased. To overcome this issue, we propose an approach to attain equity in the reputation scores computation, independently of any sensitive attribute that characterizes the users.