Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Experiences of Censorship on TikTok Across Marginalised Identities

Eddie L. Ungless, Nina Markl, Björn Ross

TL;DR

This study investigates perceived censorship on TikTok across marginalised identities using a UK-based survey of 627 respondents to examine content removal, suppression, and beliefs about algorithmic censorship. By integrating quantitative analyses with a folk-theory framework, it shows that censorship is not uniformly higher for marginalised groups, but is more likely when content aligns with typical guideline interpretations, while beliefs about censorship are shaped by everyday experiences and social identities. The authors identify key patterns across gender, trans status, sexuality, ethnicity, and disability, revealing nuanced differences in posting behavior and censorship experiences, and propose future work focused on users’ folk theories and suppression dynamics. The work highlights implications for platform governance, user well-being, and online discourse, urging attention to perceived fairness and the social-identity dynamics that drive censorship beliefs and behaviors on algorithm-driven platforms.

Abstract

TikTok has seen exponential growth as a platform, fuelled by the success of its proprietary recommender algorithm which serves tailored content to every user - though not without controversy. Users complain of their content being unfairly suppressed by ''the algorithm'', particularly users with marginalised identities such as LGBTQ+ users. Together with content removal, this suppression acts to censor what is shared on the platform. Journalists have revealed biases in automatic censorship, as well as human moderation. We investigate experiences of censorship on TikTok, across users marginalised by their gender, LGBTQ+ identity, disability or ethnicity. We survey 627 UK-based TikTok users and find that marginalised users often feel they are subject to censorship for content that does not violate community guidelines. We highlight many avenues for future research into censorship on TikTok, with a focus on users' folk theories, which greatly shape their experiences of the platform.

Experiences of Censorship on TikTok Across Marginalised Identities

TL;DR

This study investigates perceived censorship on TikTok across marginalised identities using a UK-based survey of 627 respondents to examine content removal, suppression, and beliefs about algorithmic censorship. By integrating quantitative analyses with a folk-theory framework, it shows that censorship is not uniformly higher for marginalised groups, but is more likely when content aligns with typical guideline interpretations, while beliefs about censorship are shaped by everyday experiences and social identities. The authors identify key patterns across gender, trans status, sexuality, ethnicity, and disability, revealing nuanced differences in posting behavior and censorship experiences, and propose future work focused on users’ folk theories and suppression dynamics. The work highlights implications for platform governance, user well-being, and online discourse, urging attention to perceived fairness and the social-identity dynamics that drive censorship beliefs and behaviors on algorithm-driven platforms.

Abstract

TikTok has seen exponential growth as a platform, fuelled by the success of its proprietary recommender algorithm which serves tailored content to every user - though not without controversy. Users complain of their content being unfairly suppressed by ''the algorithm'', particularly users with marginalised identities such as LGBTQ+ users. Together with content removal, this suppression acts to censor what is shared on the platform. Journalists have revealed biases in automatic censorship, as well as human moderation. We investigate experiences of censorship on TikTok, across users marginalised by their gender, LGBTQ+ identity, disability or ethnicity. We survey 627 UK-based TikTok users and find that marginalised users often feel they are subject to censorship for content that does not violate community guidelines. We highlight many avenues for future research into censorship on TikTok, with a focus on users' folk theories, which greatly shape their experiences of the platform.
Paper Structure (36 sections, 3 figures, 3 tables)

This paper contains 36 sections, 3 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Background
  3. Introduction to TikTok
  4. Biased moderation on social media
  5. Harms of (biased) algorithmic censorship
  6. Folk theories of censorship
  7. Methodology
  8. Respondents
  9. Procedure and Measurements
  10. Use of TikTok
  11. Experience of Censorship
  12. Beliefs about Algorithmic Censorship
  13. Beliefs about Community Guidelines
  14. Demographic Information
  15. Results
  16. ...and 21 more sections

Figures (3)

  • Figure 1: Chart showing the percentage of respondents by gender who posted "controversial" content, and reported having content removed or suppressed. Data labels show counts. Total counts are given after identity labels.
  • Figure 2: Chart showing percentage of respondents by sexuality who posted "controversial" content, and reported having content removed or suppressed. Data labels show counts. Total counts are given after identities.
  • Figure 3: Chart showing percentage of respondents by disability status who posted "controversial" content, and reported having content removed or suppressed. Data labels show counts. Total counts given after identities.