Home | Publications | BIY+25

Privacy-Preserving Federated Learning for Hate Speech Detection

MCML Authors

Haotian Ye

→ Group Hinrich Schütze
Computational Linguistics

Axel Wisiorek

Dr.

→ Group Hinrich Schütze
Computational Linguistics

Hinrich Schütze

Prof. Dr.

Principal Investigator

Computational Linguistics

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.

inproceedings

SRW @NAACL 2025

Student Research Workshop at the Annual Conference of the North American Chapter of the Association for Computational Linguistics. Albuquerque, NM, USA, Apr 29-May 04, 2025.