Nowadays, misogynistic abuse online has become a serious issue due, especially, to anonymity and interactivity of the web that facilitate the increase and the permanence of the offensive comments on the web. In this paper, we present an approach based on stylistic and specific topic information for the detection of misogyny, exploring the several aspects of misogynistic Spanish and English user generated texts on Twitter. Our method has been evaluated in the framework of our participation in the AMI shared task at IberEval 2018 obtaining promising results.

Exploration of Misogyny in Spanish and English tweets

Simona Frenda
First
;
Manuel Montes-y-Gómez
2018-01-01

Abstract

Nowadays, misogynistic abuse online has become a serious issue due, especially, to anonymity and interactivity of the web that facilitate the increase and the permanence of the offensive comments on the web. In this paper, we present an approach based on stylistic and specific topic information for the detection of misogyny, exploring the several aspects of misogynistic Spanish and English user generated texts on Twitter. Our method has been evaluated in the framework of our participation in the AMI shared task at IberEval 2018 obtaining promising results.
2018
Third Workshop on Evaluation of Human Language Technologies for Iberian Languages (IberEval 2018)
Sevilla, Spain
September 18th, 2018
Proceedings of the Third Workshop on Evaluation of Human Language Technologies for Iberian Languages (IberEval 2018) co-located with 34th Conference of the Spanish Society for Natural Language Processing (SEPLN 2018)
Ceur Workshop Proceedings
2150
260
267
http://ceur-ws.org/Vol-2150/AMI_paper6.pdf
Misogyny Detection NLP Linguistic Analysis
Simona Frenda, Bilal Ghanem, Manuel Montes-y-Gómez
File in questo prodotto:
File Dimensione Formato  
AMI_paper6.pdf

Accesso aperto

Tipo di file: PDF EDITORIALE
Dimensione 373.67 kB
Formato Adobe PDF
373.67 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/1676283
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 37
  • ???jsp.display-item.citation.isi??? ND
social impact