Hate Speech Recognition in Chilean Tweets

Alfonso Tobar-Arancibia, Sebastian Moreno, Javier Lopatin

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Hate speech, which targets specific groups based on race, religion, or sexual orientation, is a growing concern, especially on social media. Detecting hate speech is a critical research area, but most models are developed in English, leaving a gap for other languages like Spanish. Spanish presents additional challenges due to its regional variants and slang. In this paper, we introduce HateStack, the winning model of the 2022 Datathon at Universidad Técnica Federico Santa Maria, Chile, designed to detect hate speech in Chilean tweets. HateStack is a two-level ensemble model comprising a feature extraction process, five Level-l models, and a logistic regression as a second-level model. The results demonstrate that HateStack outperforms other ensemble models and RoBERTuito, a transformer-based deep learning model tailored for hate speech detection on tweets. Developing such models in non-English languages is important to detect hate speech effectively.

Original languageEnglish
Title of host publication2023 42nd IEEE International Conference of the Chilean Computer Science Society, SCCC 2023
PublisherIEEE Computer Society
ISBN (Electronic)9798350313895
DOIs
StatePublished - 2023
Externally publishedYes
Event42nd IEEE International Conference of the Chilean Computer Science Society, SCCC 2023 - Concepcion, Chile
Duration: 23 Oct 202326 Oct 2023

Publication series

NameProceedings - International Conference of the Chilean Computer Science Society, SCCC
ISSN (Print)1522-4902

Conference

Conference42nd IEEE International Conference of the Chilean Computer Science Society, SCCC 2023
Country/TerritoryChile
CityConcepcion
Period23/10/2326/10/23

Keywords

  • Deep Learning
  • Ensemble Models
  • Hate Speech
  • Machine Learning
  • Stacking

Fingerprint

Dive into the research topics of 'Hate Speech Recognition in Chilean Tweets'. Together they form a unique fingerprint.

Cite this