Social‑media feeds are detoxified by a redesigned algorithm

A large-scale experiment tested the impact of changing the Bluesky feed-ranking algorithm on political content and perceptions during the 2024 US presidential election. By making feeds more representative of users, the ‘diversified extremity’ algorithm reduced exposure to polarizing content and made perceptions of social norms more accurate, without reducing user enjoyment. Reverse-chronological and ‘diversified extremity’ feeds result in less uncivil content than the current engagement-based model.

Publication Details

Journal
Nature
Published
2026-05-27
DOI
https://doi.org/10.1038/d41586-026-01636-z
Primary Topic
Social Media and Politics
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Social‑media feeds are detoxified by a redesigned algorithm

Nature
Social Media and Politics
article

Social‑media feeds are detoxified by a redesigned algorithm

article en

Abstract

A large-scale experiment tested the impact of changing the Bluesky feed-ranking algorithm on political content and perceptions during the 2024 US presidential election. By making feeds more representative of users, the ‘diversified extremity’ algorithm reduced exposure to polarizing content and made perceptions of social norms more accurate, without reducing user enjoyment. Reverse-chronological and ‘diversified extremity’ feeds result in less uncivil content than the current engagement-based model.

Nature
Reduced inequalities
Openalex Percentile: Top 3%
Social Media and Politics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.