Peer-reviewed research
Gender and Dialect Bias in YouTube's Automatic Captions
Rachael Tatman, Proceedings of the First ACL Workshop on Ethics in Natural Language Processing, 2017
Read the originalRead on October 16, 2026
- What it is
- A workshop paper that compared the accuracy of YouTube's automatic captions across two genders and five dialect groups of English, using videos from the accent tag challenge.
- How much weight it carries
- A peer-reviewed workshop paper. The system tested is from 2016 and the sample is small, so the size of the gaps is dated, but it is an early, clear measurement of dialect differences.
Facts taken from this source
- A 2017 study of YouTube's automatic captions found lower accuracy for women and for speakers from Scotland.
“with lower accuracy for 1) women and 2) speakers from Scotland” (Abstract)
Pages that rest on this source
- Dictation Languages, Accents and Voice TranslationTopic
- Video to Text: Transcribe Videos and YouTubeGuide
- Dictation for Journalists and Content CreatorsGuide
- How do you add automatic captions to YouTube Shorts?Question
- How do you get the transcript of a YouTube video?Question
- Why is the YouTube transcript not showing?Question