redfrog<p>via <span class="h-card" translate="no"><a href="https://mastodon.social/@chavalarias" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>chavalarias</span></a></span> : <br>Publication <span class="h-card" translate="no"><a href="https://mamot.fr/@CNRS" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>CNRS</span></a></span> <span class="h-card" translate="no"><a href="https://mamot.fr/@Nature" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@<span>Nature</span></a></span> <br>Scientific Report: <br>Grâce au travail de @P_Bouchaud et @MaziyarPanahi et aux données <a href="https://mamot.fr/tags/Horus" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>Horus</span></a> nous avons enfin décortiqué l'algorithme de Twitter. <br>Les biais algorithmiques de <a href="https://mamot.fr/tags/ToxicData" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ToxicData</span></a> et bien d'autres choses... et c'est pas jojo😡</p><p>Crowdsourced audit of Twitter’s recommender systems<br><a href="https://www.nature.com/articles/s41598-023-43980-4" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">nature.com/articles/s41598-023</span><span class="invisible">-43980-4</span></a></p>