An audit of Twitter's shadowban sanctions in the United States

EasyChair Preprint no. 6003

Abstract

We audit Twitter's shadow ban algorithms for ideological bias, by testing the profile and content visibility for a representative sample of US users. Controlling for incivility, bot-like behavior, and network size, there is little to suggest that right wing accounts are indeed more likely to be shadow banned.

Keyphrases: polarization, Shadowban, Twitter

@Booklet{EasyChair:6003,
  author = {Kokil Jaidka and Subhayan Mukerjee and Yphtach Lelkes},
  title = {An audit of Twitter's shadowban sanctions in the United States},
  howpublished = {EasyChair Preprint no. 6003},

  year = {EasyChair, 2021}}