Crowdsourced audit of Twitter’s recommender systems
Abstract 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 ampli...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-10-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-43980-4 |
| _version_ | 1797576782251032576 |
|---|---|
| author | Paul Bouchaud David Chavalarias Maziyar Panahi |
| author_facet | Paul Bouchaud David Chavalarias Maziyar Panahi |
| author_sort | Paul Bouchaud |
| collection | DOAJ |
| description | Abstract 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. |
| first_indexed | 2024-03-10T21:58:38Z |
| format | Article |
| id | doaj.art-90a5dd74741d4de1b927708d86b1b0a4 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-03-10T21:58:38Z |
| publishDate | 2023-10-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-90a5dd74741d4de1b927708d86b1b0a42023-11-19T13:02:19ZengNature PortfolioScientific Reports2045-23222023-10-011311810.1038/s41598-023-43980-4Crowdsourced audit of Twitter’s recommender systemsPaul Bouchaud0David Chavalarias1Maziyar Panahi2CNRS, Complex Systems Institute of Paris Île-de-France (ISC-PIF)CNRS, Complex Systems Institute of Paris Île-de-France (ISC-PIF)CNRS, Complex Systems Institute of Paris Île-de-France (ISC-PIF)Abstract 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.https://doi.org/10.1038/s41598-023-43980-4 |
| spellingShingle | Paul Bouchaud David Chavalarias Maziyar Panahi Crowdsourced audit of Twitter’s recommender systems Scientific Reports |
| title | Crowdsourced audit of Twitter’s recommender systems |
| title_full | Crowdsourced audit of Twitter’s recommender systems |
| title_fullStr | Crowdsourced audit of Twitter’s recommender systems |
| title_full_unstemmed | Crowdsourced audit of Twitter’s recommender systems |
| title_short | Crowdsourced audit of Twitter’s recommender systems |
| title_sort | crowdsourced audit of twitter s recommender systems |
| url | https://doi.org/10.1038/s41598-023-43980-4 |
| work_keys_str_mv | AT paulbouchaud crowdsourcedauditoftwittersrecommendersystems AT davidchavalarias crowdsourcedauditoftwittersrecommendersystems AT maziyarpanahi crowdsourcedauditoftwittersrecommendersystems |