A Federated Approach to Few-Shot Hate Speech Detection for Marginalized Communities

Kaydedildi:
Detaylı Bibliyografya
Yayımlandı:arXiv.org (Dec 6, 2024), p. n/a
Yazar: Ye, Haotian
Diğer Yazarlar: Wisiorek, Axel, Maronikolakis, Antonis, Alaçam, Özge, Schütze, Hinrich
Baskı/Yayın Bilgisi:
Cornell University Library, arXiv.org
Konular:
Online Erişim:Citation/Abstract
Full text outside of ProQuest
Etiketler: Etiketle
Etiket eklenmemiş, İlk siz ekleyin!

MARC

LEADER 00000nab a2200000uu 4500
001 3142373769
003 UK-CbPIL
022 |a 2331-8422 
035 |a 3142373769 
045 0 |b d20241206 
100 1 |a Ye, Haotian 
245 1 |a A Federated Approach to Few-Shot Hate Speech Detection for Marginalized Communities 
260 |b Cornell University Library, arXiv.org  |c Dec 6, 2024 
513 |a Working Paper 
520 3 |a Hate speech online remains an understudied issue for marginalized communities, and has seen rising relevance, especially in the Global South, which includes developing societies with increasing internet penetration. In this paper, we aim to provide marginalized communities living in societies where the dominant language is low-resource with a privacy-preserving tool to protect themselves from hate speech on the internet by filtering offensive content in their native languages. Our contribution in this paper is twofold: 1) we release REACT (REsponsive hate speech datasets Across ConTexts), a collection of high-quality, culture-specific hate speech detection datasets comprising seven distinct target groups in eight low-resource languages, curated by experienced data collectors; 2) we propose a solution to few-shot hate speech detection utilizing federated learning (FL), a privacy-preserving and collaborative learning approach, to continuously improve a central model that exhibits robustness when tackling different target groups and languages. By keeping the training local to the users' devices, we ensure the privacy of the users' data while benefitting from the efficiency of federated learning. Furthermore, we personalize client models to target-specific training data and evaluate their performance. Our results indicate the effectiveness of FL across different target groups, whereas the benefits of personalization on few-shot learning are not clear. 
653 |a Datasets 
653 |a Hate speech 
653 |a Privacy 
653 |a Internet 
653 |a Federated learning 
653 |a Languages 
653 |a Target detection 
700 1 |a Wisiorek, Axel 
700 1 |a Maronikolakis, Antonis 
700 1 |a Alaçam, Özge 
700 1 |a Schütze, Hinrich 
773 0 |t arXiv.org  |g (Dec 6, 2024), p. n/a 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3142373769/abstract/embedded/6A8EOT78XXH2IG52?source=fedsrch 
856 4 0 |3 Full text outside of ProQuest  |u http://arxiv.org/abs/2412.04942