# TuPy-E: detecting hate speech in Brazilian Portuguese social media with a novel dataset and comprehensive analysis of models

arXiv: https://arxiv.org/abs/2312.17704 · HTML: https://mlsanity.com/paper/2312.17704/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 0 of its 3 references that are in the map.
- First posted on arXiv 29 Dec 2023.

## Built on by (most cited first, 3 of 3)

- [From Languages to Geographies: Towards Evaluating Cultural Bias in Hate Speech Datasets](https://mlsanity.com/paper/2404.17874/) (2024)
- [Bye Bye Perspective API: Lessons for Building and Governing Measurement Infrastructure](https://mlsanity.com/paper/2604.25580/) (2026)
- [NorBERTo: A ModernBERT Model Trained for Portuguese with 331 Billion Tokens Corpus](https://mlsanity.com/paper/2605.00086/) (2026)

## Abstract (arXiv)

Social media has become integral to human interaction, providing a platform for communication and expression. However, the rise of hate speech on these platforms poses significant risks to individuals and communities. Detecting and addressing hate speech is particularly challenging in languages like Portuguese due to its rich vocabulary, complex grammar, and regional variations. To address this, we introduce TuPy-E, the largest annotated Portuguese corpus for hate speech detection. TuPy-E leverages an open-source approach, fostering collaboration within the research community. We conduct a detailed analysis using advanced techniques like BERT models, contributing to both academic understanding and practical applications