Auditing the audits: evaluating methodologies for social media recommender system audits

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 friend...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Applied network science Ročník 9; číslo 1; s. 59 - 20
Hlavní autoři: Bouchaud, Paul, Ramaciotti, Pedro
Médium: Journal Article
Jazyk:angličtina
Vydáno: Cham Springer International Publishing 01.12.2024
Springer Nature B.V
Springer
SpringerOpen
Témata:
Algorithm audit
Algorithms
Auditing
Audits
Behavior
Complexity
Computer Appl. in Social and Behavioral Sciences
Computer Science
Digital media
Diversity
Humanities and Social Sciences
Ideology
Impact analysis
Parameters
Polarization
Recommender systems
Science
Simulation and Modeling
Social media
Social networks
Special Issue of the 12th International Conference on Complex Networks and their Applications
User models
Polarization
Algorithm audit
User models
Social media
Ideology
Diversity
Social media Ideology Polarization Diversity Algorithm audit User models
ISSN:2364-8228, 2364-8228
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí: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.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2364-8228
2364-8228
DOI:10.1007/s41109-024-00668-6