EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Cross-lingual hate speech detection using domain-specific word embeddings

Ayme Arango Monnar iD, Jorge Perez Rojas, Barbara Polete Labra

PLOS ONE · 2024

DOI: 10.1371/journal.pone.0306521 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS ONE, 2024. Verfasst von Ayme Arango Monnar und 2 weiteren Autor:innen. Beteiligte Einrichtung: Computer Science Department, Universidad de Chile, Santiago de Chile, Chile. Hauptthemen laut MEDLINE: Multilingualism, Natural Language Processing. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: IMFD, Fondecyt.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

THIS ARTICLE USES WORDS OR LANGUAGE THAT IS CONSIDERED PROFANE, VULGAR, OR OFFENSIVE BY SOME READERS. Hate speech detection in online social networks is a multidimensional problem, dependent on language and cultural factors. Most supervised learning resources for this task, such as labeled datasets and Natural Language Processing (NLP) tools, have been specifically tailored for English. However, a large portion of web users around the world speak different languages, creating an important need for efficient multilingual hate speech detection approaches. In particular, such approaches should be able to leverage the limited cross-lingual resources currently existing in their learning process. The cross-lingual transfer in this task has been difficult to achieve successfully. Therefore, we propose a simple yet effective method to approach this problem. To our knowledge, ours is the first attempt to create a multilingual embedding model specific to this problem. We validate the effectiveness of our approach by performing an extensive comparative evaluation against several well-known general-purpose language models that, unlike ours, have been trained on massive amounts of data. We focus on a zero-shot cross-lingual evaluation scenario in which we classify hate speech in one language without having access to any labeled data. Despite its simplicity, our embeddings outperform more complex models for most experimental settings we tested. In addition, we provide further evidence of the effectiveness of our approach through an ad hoc qualitative exploratory analysis, which captures how hate speech is displayed in different languages. This analysis allows us to find new cross-lingual relations between words in the hate-speech domain. Overall, our findings indicate common patterns in how hate speech is expressed across languages and that our proposed model can capture such relationships significantly.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MultilingualismNatural Language ProcessingHumansSpeechLanguageHate

Autor:innen und Institutionen

  • Computer Science Department, Universidad de Chile, Santiago de Chile, Chile.
  • Cero.ai, Santiago de Chile, Chile.
  • Amazon, Washington, DC, United States of America.

ORCID-Profile: Ayme Arango Monnar

Förderung

  • IMFD
  • Fondecyt

Zitieren

APA

Monnar, A. A., Perez Rojas, J., & Labra, B. P. (2024). Cross-lingual hate speech detection using domain-specific word embeddings. PLOS ONE. https://doi.org/10.1371/journal.pone.0306521

Vancouver

Monnar AA, Perez Rojas J, Labra BP. Cross-lingual hate speech detection using domain-specific word embeddings. PLOS ONE. 2024. doi:10.1371/journal.pone.0306521

BibTeX
@article{Monnar2024,
  author = {Monnar, Ayme Arango and Perez Rojas, Jorge and Labra, Barbara Polete},
  title = {Cross-lingual hate speech detection using domain-specific word embeddings},
  journal = {PLOS ONE},
  year = {2024},
  doi = {10.1371/journal.pone.0306521}
}
Kostenlos starten →