License: Creative Commons Attribution 4.0 International license (CC BY 4.0)
When quoting this document, please refer to the following
DOI: 10.4230/OASIcs.SLATE.2022.11
URN: urn:nbn:de:0030-drops-167570
URL: http://dagstuhl.sunsite.rwth-aachen.de/volltexte/2022/16757/
Go to the corresponding OASIcs Volume Portal

Santos, Raquel Bento ; Matos, Bernardo Cunha ; Carvalho, Paula ; Batista, Fernando ; Ribeiro, Ricardo

Semi-Supervised Annotation of Portuguese Hate Speech Across Social Media Domains

pdf-format:
OASIcs-SLATE-2022-11.pdf (0.5 MB)

Abstract

With the increasing spread of hate speech (HS) on social media, it becomes urgent to develop models that can help detecting it automatically. Typically, such models require large-scale annotated corpora, which are still scarce in languages such as Portuguese. However, creating manually annotated corpora is a very expensive and time-consuming task. To address this problem, we propose an ensemble of two semi-supervised models that can be used to automatically create a corpus representative of online hate speech in Portuguese. The first model combines Generative Adversarial Networks and a BERT-based model. The second model is based on label propagation, and consists of propagating labels from existing annotated corpora to the unlabeled data, by exploring the notion of similarity. We have explored the annotations of three existing corpora (CO-HATE, ToLR-BR, and HPHS) in order to automatically annotate FIGHT, a corpus composed of geolocated tweets produced in the Portuguese territory. Through the process of selecting the best model and the corresponding setup, we have tested different pre-trained embeddings, performed experiments using different training subsets, labeled by different annotators with different perspectives, and performed several experiments with active learning. Furthermore, this work explores back translation as a mean to automatically generate additional hate speech samples. The best results were achieved by combining all the labeled datasets, obtaining 0.664 F1-score for the Hate Speech class in FIGHT.

BibTeX - Entry

@InProceedings{santos_et_al:OASIcs.SLATE.2022.11,
  author =	{Santos, Raquel Bento and Matos, Bernardo Cunha and Carvalho, Paula and Batista, Fernando and Ribeiro, Ricardo},
  title =	{{Semi-Supervised Annotation of Portuguese Hate Speech Across Social Media Domains}},
  booktitle =	{11th Symposium on Languages, Applications and Technologies (SLATE 2022)},
  pages =	{11:1--11:14},
  series =	{Open Access Series in Informatics (OASIcs)},
  ISBN =	{978-3-95977-245-7},
  ISSN =	{2190-6807},
  year =	{2022},
  volume =	{104},
  editor =	{Cordeiro, Jo\~{a}o and Pereira, Maria Jo\~{a}o and Rodrigues, Nuno F. and Pais, Sebasti\~{a}o},
  publisher =	{Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik},
  address =	{Dagstuhl, Germany},
  URL =		{https://drops.dagstuhl.de/opus/volltexte/2022/16757},
  URN =		{urn:nbn:de:0030-drops-167570},
  doi =		{10.4230/OASIcs.SLATE.2022.11},
  annote =	{Keywords: Hate Speech, Semi-Supervised Learning, Semi-Automatic Annotation}
}

Keywords: Hate Speech, Semi-Supervised Learning, Semi-Automatic Annotation
Collection: 11th Symposium on Languages, Applications and Technologies (SLATE 2022)
Issue Date: 2022
Date of publication: 27.07.2022
Supplementary Material: Software (Code, Data and Models): https://hate-covid.inesc-id.pt/?page_id=200

DROPS-Home | Fulltext Search | Imprint | Privacy Published by LZI