Digital Skin, Digital Bias: Uncovering Tone-Based Biases in LLMs and Emoji Embeddings
Open Access
- 12 April 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1662-1671
Abstract
No abstract availableAll Related Versions
This publication has 18 references indexed in Scilit:
- Five sources of bias in natural language processingLanguage and Linguistics Compass, 2021
- The Whiteness of AIPhilosophy & Technology, 2020
- New Emoji Requests from Twitter UsersACM Transactions on Social Computing, 2020
- Robotics Has a Race ProblemScience, Technology, & Human Values, 2019
- Rehumanized Crowdsourcing2019
- Actionable Auditing2019
- Repurposing Emoji for Personalised Communication2018
- Word embeddings quantify 100 years of gender and ethnic stereotypesProceedings of the National Academy of Sciences, 2018
- “Turn that frown upside-down”: A contextual account of emoticon usage on different virtual platformsComputers in Human Behavior, 2016
- Beyond the pale: The Blackbird web browser’s critical receptionNew Media & Society, 2011