Analyzing Zero-Shot transfer Scenarios across Spanish variants for Hate Speech Detection

in Scientific publications
Share this publication
Author Galo Castillo-lópez, Arij Riabi, Djamé Seddah
Title of Journal, Proc. or Book Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023)
Issue 1 May 2023
DOI 10.18653/v1/2023.vardial-1.1
Repository link
Peer reviewed Yes
Open access Yes

Hate speech detection in online platforms has been widely studied inthe past. Most of these works were conducted in English and afew rich-resource languages. Recent approaches tailored forlow-resource languages have explored the interests of zero-shot cross-lingual transfer learning models in resource-scarce scenarios. However, languages variations between geolects such as AmericanEnglish and British English, Latin-American Spanish, and EuropeanSpanish is still a problem for NLP models that often relies on(latent) lexical information for their classification tasks. Moreimportantly, the cultural aspect, crucial for hate speech detection,is often overlooked. In this work, we present the results of a thorough analysis of hatespeech detection models performance on different variants of Spanish,including a new hate speech toward immigrants Twitter data set we built to cover these variants. Using mBERT and Beto, a monolingual Spanish Bert-based language model, as the basis of our transfer learning architecture, our results indicate that hate speech detection models for a given Spanish variant are affected when different variations of such language are not considered. Hate speech expressions could vary from region to region where the same language is spoken. Our new dataset, models and guidelines are freely available.


Previous Post
EU H2020 project privacy-first situational awareness platform for violent terrorism and crime prediction, counter radicalisation and citizen protection (CounteR)
Next Post
Enriching the NArabizi Treebank: A Multifaceted Approach to Supporting an Under-Resourced Language
You may also be interested in these topics
Skip to content