Display options
Share it on

Cognit Comput. 2021 Jun 28;1-31. doi: 10.1007/s12559-021-09862-5. Epub 2021 Jun 28.

Emotionally Informed Hate Speech Detection: A Multi-target Perspective.

Cognitive computation

Patricia Chiril, Endang Wahyu Pamungkas, Farah Benamara, Véronique Moriceau, Viviana Patti

Affiliations

  1. IRIT, Université de Toulouse, Université Toulouse III - UPS, Toulouse, France.
  2. Dipartimento di Informatica, University of Turin, Turin, Italy.

PMID: 34221180 PMCID: PMC8236572 DOI: 10.1007/s12559-021-09862-5

Abstract

Hate Speech and harassment are widespread in online communication, due to users' freedom and anonymity and the lack of regulation provided by social media platforms. Hate speech is topically focused (misogyny, sexism, racism, xenophobia, homophobia, etc.), and each specific manifestation of hate speech targets different vulnerable groups based on characteristics such as gender (misogyny, sexism), ethnicity, race, religion (xenophobia, racism, Islamophobia), sexual orientation (homophobia), and so on. Most automatic hate speech detection approaches cast the problem into a binary classification task without addressing either the

© The Author(s) 2021.

Keywords: Affective resources; Hate speech detection; Hate speech targets; Multi-task learning; Social media

Conflict of interest statement

Conflicts of InterestAll authors state that there are no conflicts of interest.

References

  1. PLoS One. 2020 Dec 28;15(12):e0243300 - PubMed
  2. Neural Comput. 1997 Nov 15;9(8):1735-80 - PubMed
  3. Minds Mach (Dordr). 2018;28(4):689-707 - PubMed
  4. Sci Eng Ethics. 2020 Jun;26(3):1771-1796 - PubMed
  5. EPJ Data Sci. 2016;5(1):11 - PubMed

Publication Types