Crowdsourced audit of Twitter's recommender systems.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
05 10 2023
05 10 2023
Historique:
received:
03
05
2023
accepted:
01
10
2023
medline:
1
11
2023
pubmed:
6
10
2023
entrez:
5
10
2023
Statut:
epublish
Résumé
This research conducts an audit of Twitter's recommender system, aiming to examine the disparities between users' curated timelines and their subscription choices. Through the combined use of a browser extension and data collection via the Twitter API, our investigation reveals a high amplification of friends from the same community, a preference for amplifying emotionally charged and toxic tweets and an uneven algorithmic amplification across friends' political leaning. This audit emphasizes the importance of transparency, and increased awareness regarding the impact of algorithmic curation.
Identifiants
pubmed: 37798318
doi: 10.1038/s41598-023-43980-4
pii: 10.1038/s41598-023-43980-4
pmc: PMC10556069
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
16815Informations de copyright
© 2023. Springer Nature Limited.
Références
Proc Natl Acad Sci U S A. 2018 Sep 11;115(37):9216-9221
pubmed: 30154168
Proc Natl Acad Sci U S A. 2022 Jan 4;119(1):
pubmed: 34934011
PLoS One. 2018 Sep 19;13(9):e0201879
pubmed: 30231018
KDD. 2016 Aug;2016:855-864
pubmed: 27853626
Nature. 2021 Jul;595(7866):197-204
pubmed: 34194046