Auditing the audits: evaluating methodologies for social media recommender system audits
Applied Network Science · 16.09.2024 · 9 (1)
DOI: 10.1007/s41109-024-00668-6 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Network Science, online erschienen am 16.09.2024. Verfasst von Paul Bouchaud und 1 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: CFM Foundation for Research, EU‘s Horizon 2020 programme, French National Agency for Research.
Abstract (Originalsprache)
Through a simulated Twitter-like platform designed to optimize user engagement and grounded in authentic behavioral data, this study evaluates methodologies for auditing social media recommender systems. Our analysis focuses on the impact of key parameters in sock-puppet audits, the number of friends and session length, on audit outcomes. Additionally, we investigate the algorithmic amplification of political content across different levels of granularity, segmenting users based on political leanings and considering multiple political dimensions beyond declared affiliations. Our findings underscore the necessity of employing realistic parameter settings in audits and highlight the importance of nuanced political segmentation. Amid increasing regulatory scrutiny, this research contributes to enhancing methodologies for auditing social media platforms.
Förderung
- CFM Foundation for Research
- EU‘s Horizon 2020 programme
- French National Agency for Research
- SoMe4Dem
Zitieren
APA
Bouchaud, P., & Ramaciotti, P. (2024). Auditing the audits: evaluating methodologies for social media recommender system audits. Applied Network Science, 9(1). https://doi.org/10.1007/s41109-024-00668-6
Vancouver
Bouchaud P, Ramaciotti P. Auditing the audits: evaluating methodologies for social media recommender system audits. Applied Network Science. 2024;9(1). doi:10.1007/s41109-024-00668-6
BibTeX
@article{Bouchaud2024,
author = {Bouchaud, Paul and Ramaciotti, Pedro},
title = {Auditing the audits: evaluating methodologies for social media recommender system audits},
journal = {Applied Network Science},
year = {2024},
volume = {9},
number = {1},
doi = {10.1007/s41109-024-00668-6}
}
EUVIMED