Despite the number of approaches recently proposed in NLP for detecting abusive language on social networks, the issue of developing hate speech detection systems that are robust across different platforms is still an unsolved problem. In this paper we perform a comparative evaluation on datasets for hate speech detection in Italian, extracted from four different social media platforms, i.e. Facebook, Twitter, Instagram and WhatsApp. We show that combining such platform-dependent datasets to take advantage of training data developed for other platforms is beneficial, although their impact varies depending on the social network under consideration.

Cross-Platform Evaluation for Italian Hate Speech Detection

Stefano Menini
;
Elena Cabrio
;
Sara Tonelli
;
2019-01-01

Abstract

Despite the number of approaches recently proposed in NLP for detecting abusive language on social networks, the issue of developing hate speech detection systems that are robust across different platforms is still an unsolved problem. In this paper we perform a comparative evaluation on datasets for hate speech detection in Italian, extracted from four different social media platforms, i.e. Facebook, Twitter, Instagram and WhatsApp. We show that combining such platform-dependent datasets to take advantage of training data developed for other platforms is beneficial, although their impact varies depending on the social network under consideration.
File in questo prodotto:
File Dimensione Formato  
paper22.pdf

accesso aperto

Tipologia: Documento in Post-print
Licenza: Dominio pubblico
Dimensione 286.02 kB
Formato Adobe PDF
286.02 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/11582/320600
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
social impact