Inequality and Inequity in Network-based Ranking and Recommendation Algorithms

Abstract

Though algorithms promise many benefits including efficiency, objectivity and accuracy, they may also introduce or amplify biases. Here we study two well-known algorithms, namely PageRank and Who-to-Follow (WTF), and show to what extent their ranks produce inequality and inequity when applied to directed social networks. To this end, we propose a directed network model with preferential attachment and homophily (DPAH) and demonstrate the influence of network structure on the rank distributions of these algorithms. Our main findings suggest that (i) inequality is positively correlated with inequity, (ii) inequality is driven by the interplay between preferential attachment, homophily, node activity and edge density, and (iii) inequity is driven by the interplay between homophily and minority size. In particular, these two algorithms reduce, replicate and amplify the representation of minorities in top ranks when majorities are homophilic, neutral and heterophilic, respectively. Moreover, when this representation is reduced, minorities may improve their visibility in the rank by connecting strategically in the network. For instance, by increasing their out-degree or homophily when majorities are also homophilic. These findings shed light on the social and algorithmic mechanisms that hinder equality and equity in network-based ranking and recommendation algorithms.

23 pages, 7 figures and 3 tables in main manuscript. Includes supplementary material

References in corpus (3)

• Activity driven modeling of time varying networks
• PageRank for ranking authors in co-citation networks
• The Paradox of Second-Order Homophily in Networks

Cited by in corpus (8)

• Unlearning Protected User Attributes in Recommendations with Adversarial Training
• Link recommendations: Their impact on network structure and minorities
• Improving the visibility of minorities through network growth interventions
• Intersectional inequalities in social networks
• hyperFA*IR: A hypergeometric approach to fair rankings with finite candidate pool
• A generative model for community types in directed networks
• Network Inequality through Preferential Attachment, Triadic Closure, and Homophily
• Emergence of social hierarchies in a society with two competitive groups