Bouchaud Paul, Chavalarias David, Panahi Maziyar
CNRS, Complex Systems Institute of Paris Île-de-France (ISC-PIF), 75013, Paris, France.
EHESS, Center for Social Analysis and Mathematics (CAMS), 75006, Paris, France.
Sci Rep. 2023 Oct 5;13(1):16815. doi: 10.1038/s41598-023-43980-4.
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.
本研究对推特的推荐系统进行了审查，旨在探究用户精心挑选的推文列表与其订阅选择之间的差异。通过结合使用浏览器扩展程序以及通过推特应用程序编程接口进行数据收集，我们的调查发现，来自同一社区的好友被高度放大推荐，推荐倾向于放大情绪化和有害的推文，并且在好友的政治倾向上存在算法放大不均衡的情况。此次审查强调了透明度的重要性，以及提高对算法筛选影响的认识。
