Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Analyzing Hate Speech Data along Racial, Gender and Intersectional Axes

Domain:

natural language processing

Record type:

paper
Creator:
MarBaaSch
Publisher:
arXiv
Host:avatar
To tackle the rising phenomenon of hate speech, efforts have been made towards data curation and analysis. When it comes to analysis of bias, previous work has focused predominantly on race. In our work, we further investigate bias in hate speech datasets along racial, gender and intersectional axes. We identify strong bias against African American English (AAE), masculine and AAE+Masculine tweets, which are annotated as disproportionately more hateful and offensive than from other demographics. We provide evidence that BERT-based models propagate this bias and show that balancing the training data for these protected attributes can lead to fairer models with regards to gender, but not race. Accepted at "4th Workshop on Gender Bias in Natural Language Processing", NAACL 2022

Visit

doi.orgarxiv.org

Tasks

hate speech detectiontext classification

Tags

Computation and Language (cs.CL)Artificial Intelligence (cs.AI)Machine Learning (cs.LG)FOS: Computer and information sciencesFOS: Computer and information sciences

Licenses

Creative Commons Attribution Share Alike 4.0 Internationalhttps://creativecommons.org/licenses/by-sa/4.0/legalcode

Similar

Intersectional Bias in Hate Speech and Abusive Language DatasetsDemoting Racial Bias in Hate Speech DetectionRacial Bias in Hate Speech and Abusive Language Detection DatasetsThe Risk of Racial Bias in Hate Speech DetectionHate Speech Detection and Racial Bias Mitigation in Social Media based on BERT modelMEDIA AND HATE SPEECH: A DISCURSIVE STUDY OF HATE SPEECH ON NAIRALAND FORUM وسائل الإعلام وخطاب الكراهية: دراسة استطرادية لخطاب الكراهية في منتدى نيرالاند MEDIA AND HATE SPEECH: A DISCURSIVE STUDY OF HATE SPEECH ON NAIRALAND FORUM MEDIA AND HATE SPEECH : A DISCURSIVE STUDY OF HATE SPEECH ON NAIRALAND FORUM MEDIA AND HATE SPEECH: A DISCURSIVE STUDY OF HATE SPEECH ON NAIRALAND FORUM

Intersectional Bias in Hate Speech and Abusive Language Datasets

Algorithms are widely applied to detect hate speech and abusive language in social media. We investi

Demoting Racial Bias in Hate Speech Detection

In current hate speech datasets, there exists a high correlation between annotators' perceptions of

Racial Bias in Hate Speech and Abusive Language Detection Datasets

Technologies for abusive language detection are being developed and applied with little consideratio

The Risk of Racial Bias in Hate Speech Detection

We investigate how annotators{'} insensitivity to differences in dialect can lead to racial bias in automatic hate speech detection models, potentially amplifying harm against minority populations. We first uncover unexpected correlations between surface markers of

Hate Speech Detection and Racial Bias Mitigation in Social Media based on BERT model

Disparate biases associated with datasets and trained classifiers in hateful and abusive content ide

MEDIA AND HATE SPEECH: A DISCURSIVE STUDY OF HATE SPEECH ON NAIRALAND FORUM وسائل الإعلام وخطاب الكراهية: دراسة استطرادية لخطاب الكراهية في منتدى نيرالاند MEDIA AND HATE SPEECH: A DISCURSIVE STUDY OF HATE SPEECH ON NAIRALAND FORUM MEDIA AND HATE SPEECH : A DISCURSIVE STUDY OF HATE SPEECH ON NAIRALAND FORUM MEDIA AND HATE SPEECH: A DISCURSIVE STUDY OF HATE SPEECH ON NAIRALAND FORUM

Digital communication has dominated a major space in our everyday discourses; reflecting how we crea