Elamur Research⌕
☰
home / papers / 2026 / Challenger at MultiPRIDE: Is It Hate Speech or Reclaimed?

Challenger at MultiPRIDE: Is It Hate Speech or Reclaimed?

Paper · 2026 · Hadi Bayrami Asl Tekanlou, Mahdi Bakhtiyarzadeh and Jafar Razmara

Summary

The paper tackles a subtask of hate speech detection: deciding whether an LGBTQ+-related slur in a tweet is used to attack or is reclaimed by the community itself. Automatic classifiers often mistake in-group reclaimed usage for abuse. The authors built a lightweight, language-agnostic pipeline for the MultiPRIDE shared task at EVALITA 2026, which covers English, Italian and Spanish tweets labelled as reclaimed or not reclaimed. Their pipeline has five steps:

  • cleaning tweets by removing URLs, mentions and non-ASCII characters, and stripping hashtag symbols;
  • stratified train/validation splitting;
  • back-translation augmentation;
  • dense embeddings from intfloat/e5-large-v2;
  • label-noise filtering with Cleanlab and logistic regression, followed by a small MLP classifier.

Italian gave the best result, with macro F1 around 0.88. English and Spanish were considerably weaker, mainly because the system struggled to detect the rare reclaimed class. The authors attribute this to severe class imbalance. The work shows that a cheap, interpretable embedding-plus-classifier system can work for this task without fine-tuning large models. The authors suggest larger embedding or generative models as future directions.

Key points

  • Dataset size: The MultiPRIDE data is split into train/development sets as follows:
    • English: 769/257 tweets
    • Italian: 814/272 tweets
    • Spanish: 657/219 tweets
  • Tools: The pipeline uses intfloat/e5-large-v2 embeddings, cleanlab's CleanLearning with logistic regression for noisy-label filtering, and back-translation via the Google Translate API (deep_translator).
  • Macro F1 by language: Italian 0.8815, Spanish 0.6773, English 0.6203.
  • Reclaimed-class (class 1) F1: Italian 0.806, Spanish 0.519, English 0.309. These low scores highlight the imbalance problem.
  • Competition context: 19 teams took part in the shared task, and no official baselines were reported.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓University of TabrizTabriz · Iran2 works · 7 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 18,614 worksArtificial Intelligence · 17,965 worksSocial Sciences · 1,954 worksSociology and Political Science · 626 works

🧭 Topics 2Research subjects and languages the work is about.Sentiment & emotion · 1,035 worksBias, fairness & safety · 587 works

Cite

Cite as Hadi Bayrami Asl Tekanlou, Mahdi Bakhtiyarzadeh and Jafar Razmara. 2026. Challenger at MultiPRIDE: Is It Hate Speech or Reclaimed?. Proceedings of the Ninth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2026).

The paper itself, not this page. BibTeX from the library's record of the work.

@inproceedings{tekanlou2026challenger,
  title = {{Challenger at MultiPRIDE: Is It Hate Speech or Reclaimed?}},
  author = {Hadi Bayrami Asl Tekanlou, Mahdi Bakhtiyarzadeh and Jafar Razmara},
  booktitle = {Proceedings of the Ninth Evaluation Campaign of Natural Language Processing and Speech Tools for Italian. Final Workshop (EVALITA 2026)},
  year = {2026},
  url = {https://aclanthology.org/2026.evalita-1.21/}
}

References

12 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. A. Albladi, M. Islam, A. Das, M. Bigonah, Z. Zhang, F. Jamshidi, M. Rahgouy, N. Raychawdhary, D. Marghitu, C. Seals, Hate speech detection using large language models: A comprehensive review, IEEE Access 13 (2025) 20871–20892. doi: 10.1109/ACCESS.2025.3532397 . — [doi:10.1109/access.2025.3532397](https://doi.org/10.1109/access.2025.3532397) find
  2. A. Schmidt, M. Wiegand, A survey on hate speech detection using natural language processing, in: L.-W. Ku, C.-T. Li (Eds.), Proceedings of the Fifth International Workshop on Natural Language Processing for Social Media, Association for Computational Linguistics, Valencia, Spain, 2017, pp. 1–10. URL…
  3. A. Tontodimamma, E. Nissi, A. Sarra, L. Fontanella, Thirty years of research into hate speech: topics of interest and their evolution, Scientometrics 126 (2021) 157–179. URL: https://doi.org/10. 1007/s11192-020-03737-6. doi: 10.1007/s11192-020-03737-6 . — [doi:10.1007/s11192-020-03737-6](https://doi.org/10.1007/s11192-020-03737-6) find
  4. A. B. De Oliveira, C. d. S. Baptista, A. A. Firmino, A. C. De Paiva, A large language model approach to detect hate speech in political discourse using multiple language corpora, in: Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing, SAC ’24, Association for Computing Machinery, New… — [doi:10.1145/3605098.3635964](https://doi.org/10.1145/3605098.3635964) find
  5. A. Toktarova, D. Syrlybay, B. Myrzakhmetova, G. Anuarbekova, G. Rakhimbayeva, B. Zhylanbaeva, N. Suieuova, M. Kerimbekov, Hate speech detection in social networks using machine learning and deep learning methods, International Journal of Advanced Computer Science and Applications 14 (2023). URL: htt… — [doi:10.14569/ijacsa.2023.0140542](https://doi.org/10.14569/ijacsa.2023.0140542) find
  6. E. Zsisku, A. Zubiaga, H. Dubossarsky, Hate speech detection and reclaimed language: Mitigating false positives and compounded discrimination, in: Proceedings of the 16th ACM Web Science Conference (WEBSCI ’24), ACM, Stuttgart, Germany, 2024, pp. 241–249. doi: 10.1145/3614419. 3644025 . — [doi:10.1145/3614419](https://doi.org/10.1145/3614419) find
  7. M. Mozafari, R. Farahbakhsh, N. Crespi, Hate speech detection and racial bias mitigation in social media based on bert model, PLOS ONE 15 (2020) 1–26. URL: https://doi.org/10.1371/journal.pone. 0237861. doi: 10.1371/journal.pone.0237861 . ↗
  8. M. ElSherief, V. Kulkarni, D. Nguyen, W. Y. Wang, E. Belding, Hate lingo: A target-based linguistic analysis of hate speech in social media, 2018. URL: https://arxiv.org/abs/1804.04257. arXiv:1804.04257 . — [arXiv:1804.04257](https://arxiv.org/abs/1804.04257) ↗
  9. J. M. Pérez, F. M. Luque, D. Zayat, M. Kondratzky, A. Moro, P. S. Serrati, J. Zajac, P. Miguel, N. Debandi, A. Gravano, V. Cotik, Assessing the impact of contextual information in hate speech detection, IEEE Access 11 (2023) 30575–30590. doi: 10.1109/ACCESS.2023.3258973 . — [doi:10.1109/access.2023.3258973](https://doi.org/10.1109/access.2023.3258973) find
  10. C. Ferrando, L. Draetta, M. Madeddu, M. Sosto, V. Patti, P. Rosso, C. Bosco, J. Mata, E. Gualda, Multipride at evalita 2026: Overview of the multilingual automatic detection of slur reclamation in the lgbtq+ context task, in: Proceedings of the Ninth Evaluation Campaign of Natural Language Processin… find
  11. D. Nozza, A. Cignarella, G. Damo, T. Caselli, V. Patti, Hodi at evalita 2023: Overview of the first shared task on homotransphobia detection in italian, in: M. Lai, S. Menini, M. Polignano, V. Russo, R. Sprugnoli, G. Venturi (Eds.), Proceedings of the Eighth Evaluation Campaign of Natural Language P… find
  12. L. Wang, N. Yang, X. Huang, B. Jiao, L. Yang, D. Jiang, R. Majumder, F. Wei, Text embeddings by weakly-supervised contrastive pre-training, arXiv preprint arXiv:2212.03533 (2022).

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/tekanlou-2026-challenger-multipride-is-it-hate/