English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Fairness is an emerging and challenging topic in recommender systems. Inrecent years, various ways of evaluating and therefore improving fairness haveemerged. In this study, we examine existing evaluation measures of fairness inrecommender systems. Specifically, we focus solely on exposure-based fairnessmeasures of individual items that aim to quantify the disparity in howindividual items are recommended to users, separate from item relevance tousers. We gather all such measures and we critically analyse their theoreticalproperties. We identify a series of limitations in each of them, whichcollectively may render the affected measures hard or impossible to interpret,to compute, or to use for comparing recommendations. We resolve theselimitations by redefining or correcting the affected measures, or we argue whycertain limitations cannot be resolved. We further perform a comprehensiveempirical analysis of both the original and our corrected versions of thesefairness measures, using real-world and synthetic datasets. Our analysisprovides novel insights into the relationship between measures based ondifferent fairness concepts, and different levels of measure sensitivity andstrictness. We conclude with practical suggestions of which fairness measuresshould be used and when. Our code is publicly available. To our knowledge, thisis the first critical comparison of individual item fairness measures inrecommender systems.

Evaluation Measures of Individual Item Fairness for Recommender Systems: A Critical Study