Detecting Hate Speech Towards the LGBT+ Population in Mexican Spanish Using Transformer Architectures

Research output: Chapter in Book or Conference Publication/ProceedingConference Publicationpeer-review

Abstract

In the context of increasing hate speech on social media platforms, this paper examines the effectiveness of various transformer-based models for detecting hate speech towards the LGBT+ community in Mexican Spanish. By focusing on tweets related to the LGBT+ community, we aim to identify the most effective model architecture for analyzing nuanced hate speech and complex language patterns. We compare the performance of pre-trained multilingual transformer models, including mBERT and XLM-RoBERTa, and address the challenges posed by class imbalance and linguistic diversity. Our findings demonstrate that DistilBERT, fine-tuned for Spanish, achieves the highest macro F1-score of 0.89, outperforming other models in accurately detecting hate speech. We also discuss strategies for handling data imbalance and provide an error analysis to highlight the limitations and potential biases of the models. Our research advocates for the deployment of these models to create safer online environments, enhancing user interaction and inclusivity across digital platforms.

Original languageEnglish
Title of host publicationSpeech and Language Technologies for Low-Resource Languages - 3rd International Conference, SPELLL 2024, Revised Selected Papers
EditorsBharathi Raja Chakravarthi, Bharathi B, Saranya Rajiakodi, Miguel Ángel García Cumbreras, Salud María Jiménez Zafra, György Kovács, Steffen Eger, Endang Wahyu Pamungkas, Kaja Dobrovoljc
PublisherSpringer Science and Business Media Deutschland GmbH
Pages397-407
Number of pages11
ISBN (Print)9783032058546
DOIs
Publication statusPublished - 2026
Event3rd International Conference on Speech and Language Technologies for Low-Resource Languages, SPELLL 2024 - Chennai, India
Duration: 4 Dec 20246 Dec 2024

Publication series

NameCommunications in Computer and Information Science
Volume2656 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference3rd International Conference on Speech and Language Technologies for Low-Resource Languages, SPELLL 2024
Country/TerritoryIndia
CityChennai
Period4/12/246/12/24

Keywords

  • Hate Speech Detection
  • LGBT+ Community
  • Mexican Spanish
  • Online Safety
  • Social Media
  • Transformer Models

Fingerprint

Dive into the research topics of 'Detecting Hate Speech Towards the LGBT+ Population in Mexican Spanish Using Transformer Architectures'. Together they form a unique fingerprint.

Cite this