@inproceedings{junior-etal-2025-privacy,
title = "Privacy-Preserving Federated Learning for Hate Speech Detection",
author = {de Souza Bueno J{\'u}nior, Ivo and
Ye, Haotian and
Wisiorek, Axel and
Sch{\"u}tze, Hinrich},
editor = "Ebrahimi, Abteen and
Haider, Samar and
Liu, Emmy and
Haider, Sammar and
Leonor Pacheco, Maria and
Wein, Shira",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)",
month = apr,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-srw.13/",
doi = "10.18653/v1/2025.naacl-srw.13",
pages = "129--141",
ISBN = "979-8-89176-192-6",
abstract = "This paper presents a federated learning system with differential privacy for hate speech detection, tailored to low-resource languages. By fine-tuning pre-trained language models, ALBERT emerged as the most effective option for balancing performance and privacy. Experiments demonstrated that federated learning with differential privacy performs adequately in low-resource settings, though datasets with fewer than 20 sentences per client struggled due to excessive noise. Balanced datasets and augmenting hateful data with non-hateful examples proved critical for improving model utility. These findings offer a scalable and privacy-conscious framework for integrating hate speech detection into social media platforms and browsers, safeguarding user privacy while addressing online harm."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="junior-etal-2025-privacy">
<titleInfo>
<title>Privacy-Preserving Federated Learning for Hate Speech Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ivo</namePart>
<namePart type="family">de Souza Bueno Júnior</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haotian</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Axel</namePart>
<namePart type="family">Wisiorek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hinrich</namePart>
<namePart type="family">Schütze</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abteen</namePart>
<namePart type="family">Ebrahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emmy</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sammar</namePart>
<namePart type="family">Haider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Leonor Pacheco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shira</namePart>
<namePart type="family">Wein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-192-6</identifier>
</relatedItem>
<abstract>This paper presents a federated learning system with differential privacy for hate speech detection, tailored to low-resource languages. By fine-tuning pre-trained language models, ALBERT emerged as the most effective option for balancing performance and privacy. Experiments demonstrated that federated learning with differential privacy performs adequately in low-resource settings, though datasets with fewer than 20 sentences per client struggled due to excessive noise. Balanced datasets and augmenting hateful data with non-hateful examples proved critical for improving model utility. These findings offer a scalable and privacy-conscious framework for integrating hate speech detection into social media platforms and browsers, safeguarding user privacy while addressing online harm.</abstract>
<identifier type="citekey">junior-etal-2025-privacy</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-srw.13</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-srw.13/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>129</start>
<end>141</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Privacy-Preserving Federated Learning for Hate Speech Detection
%A de Souza Bueno Júnior, Ivo
%A Ye, Haotian
%A Wisiorek, Axel
%A Schütze, Hinrich
%Y Ebrahimi, Abteen
%Y Haider, Samar
%Y Liu, Emmy
%Y Haider, Sammar
%Y Leonor Pacheco, Maria
%Y Wein, Shira
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-192-6
%F junior-etal-2025-privacy
%X This paper presents a federated learning system with differential privacy for hate speech detection, tailored to low-resource languages. By fine-tuning pre-trained language models, ALBERT emerged as the most effective option for balancing performance and privacy. Experiments demonstrated that federated learning with differential privacy performs adequately in low-resource settings, though datasets with fewer than 20 sentences per client struggled due to excessive noise. Balanced datasets and augmenting hateful data with non-hateful examples proved critical for improving model utility. These findings offer a scalable and privacy-conscious framework for integrating hate speech detection into social media platforms and browsers, safeguarding user privacy while addressing online harm.
%R 10.18653/v1/2025.naacl-srw.13
%U https://aclanthology.org/2025.naacl-srw.13/
%U https://doi.org/10.18653/v1/2025.naacl-srw.13
%P 129-141
Markdown (Informal)
[Privacy-Preserving Federated Learning for Hate Speech Detection](https://aclanthology.org/2025.naacl-srw.13/) (de Souza Bueno Júnior et al., NAACL 2025)
ACL
- Ivo de Souza Bueno Júnior, Haotian Ye, Axel Wisiorek, and Hinrich Schütze. 2025. Privacy-Preserving Federated Learning for Hate Speech Detection. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 4: Student Research Workshop), pages 129–141, Albuquerque, USA. Association for Computational Linguistics.