Combining mitigation treatments against biases in personalized rankings: use case on item popularity

Boratto L.;Fenu Gianni;Marras Mirko
2021-01-01

Abstract

Historical interactions leveraged by recommender systems are often non-uniformly distributed across items. Though they are of interest for consumers, certain items end up therefore being biasedly under-recommended. Existing treatments for mitigating these biases act at a single step of the pipeline (either pre-, in-, or post-processing), and it remains unanswered whether simultaneously introducing treatments throughout the pipeline leads to a better mitigation. In this paper, we analyze the impact of bias treatments along the steps of the pipeline under a use case on popularity bias. Experiments show that, with small losses in accuracy, the combination of treatments leads to better trade-offs than treatments applied separately. Our findings call for treatments rooting out bias at different steps simultaneously.
2021
Inglese
CEUR Workshop Proceedings, Proceedings of the 11th Italian Information Retrieval Workshop 2021 (IIR 2021)
CEUR-WS
Vito Walter Anelli, Tommaso Di Noia, Nicola Ferro, Fedelucio Narducci
2947
6
https://ceur-ws.org/Vol-2947/paper18.pdf
11th Italian Information Retrieval Workshop, IIR 2021
Comitato scientifico
13-15 September , 2021
Bari, Italy
internazionale
scientifica
Discrimination; Fairness; Mitigation; Rankings; Recommender systems
4 Contributo in Atti di Convegno (Proceeding)::4.1 Contributo in Atti di convegno
Boratto, L.; Fenu, Gianni; Marras, Mirko
273
3
4.1 Contributo in Atti di convegno
open
info:eu-repo/semantics/conferencePaper
Files in This Item:
File Size Format  
paper18.pdf

open access

Type: versione editoriale
Size 639.72 kB
Format Adobe PDF
639.72 kB Adobe PDF View/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Questionnaire and social

Share on:
Impostazioni cookie