A Multitask Transformer for Offensive Language Detection and Target Identification in HateBR

Guilherme Silva, Pedro Silva, Matheus Peixoto, Gladston Moreira, Eduardo Luz


Abstract
Hate speech detection is often treated as a binary task, ignoring the hierarchical nature of toxicity, such as severity levels and specific target groups. This work presents a Multitask Learning (MTL) approach for the HateBR dataset, utilizing a shared BERTimbau encoder to simultaneously predict binary offensiveness, ordinal severity, and hate speech targets. Our experiments demonstrate that the MTL architecture outperforms Single-Task baselines on the primary offensive detection task, increasing the Matthews Correlation Coefficient from 0.80 to 0.82. Beyond predictive performance, we show that joint training implicitly enforces hierarchical sanity: the unified model yields a 0% target-inconsistency rate (i.e., no cases where a comment is predicted Non-offensive while still assigned a hate target). However, we observe negative transfer in the fine-grained multilabel target task (Micro-F1 drops from 0.59 to 0.42), highlighting a trade-off between logical consistency and target attribution under extreme imbalance.
Anthology ID:
2026.propor-1.109
Volume:
Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1
Month:
April
Year:
2026
Address:
Salvador, Brazil
Editors:
Marlo Souza, Iria de-Dios-Flores, Diana Santos, Larissa Freitas, Jackson Wilke da Cruz Souza, Eugénio Ribeiro
Venue:
PROPOR
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1049–1054
Language:
URL:
https://aclanthology.org/2026.propor-1.109/
DOI:
Bibkey:
Cite (ACL):
Guilherme Silva, Pedro Silva, Matheus Peixoto, Gladston Moreira, and Eduardo Luz. 2026. A Multitask Transformer for Offensive Language Detection and Target Identification in HateBR. In Proceedings of the 17th International Conference on Computational Processing of Portuguese (PROPOR 2026) - Vol. 1, pages 1049–1054, Salvador, Brazil. Association for Computational Linguistics.
Cite (Informal):
A Multitask Transformer for Offensive Language Detection and Target Identification in HateBR (Silva et al., PROPOR 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.propor-1.109.pdf