Crowdsourced Audit of Twitter’s Recommender Systems Impact on Information Landscapes. - Institut Curie Access content directly
Preprints, Working Papers, ... Year : 2023

Crowdsourced Audit of Twitter’s Recommender Systems Impact on Information Landscapes.

Audit crowdsourcé de l'impact des systèmes de recommandation de Twitter sur les paysages de l'information.

Abstract

Combining crowd-sourced data donation and a largescale server-side data collection, we provide quantitative experimental evidence of Twitter recommender distortion of users' environment reality. Twitter's algorithmically curated home feed amplifies toxic and sentimentally valenced tweets, distorts the political landscape perceived by the users, and favors small and/or usually quiet accounts. We argue the need of independent audits of social media platforms with access to large-scale data.
Fichier principal
Vignette du fichier
horus_twitter_bias_main.pdf (215.57 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-04036232 , version 1 (19-03-2023)
hal-04036232 , version 2 (24-03-2023)
hal-04036232 , version 3 (03-07-2023)
hal-04036232 , version 4 (01-10-2023)

Identifiers

  • HAL Id : hal-04036232 , version 3

Cite

Paul Bouchaud, David Chavalarias, Maziyar Panahi. Crowdsourced Audit of Twitter’s Recommender Systems Impact on Information Landscapes.. 2023. ⟨hal-04036232v3⟩
604 View
223 Download

Share

Gmail Mastodon Facebook X LinkedIn More