Using Multilingual Approach in Cross-Lingual Transfer Learning to Improve Hate Speech Detection

Aillkeen de Oliveira, Cláudio Baptista, Anderson Firmino, Anselmo Cardoso de Paiva

2023

Abstract

In the Internet age people are increasingly connected. They have complete freedom of speech, being able to share their opinions with the society on social media. However, freedom of speech is often used to spread hate speech. This type of behavior can lead to criminality and may result in negative psychological effects. Therefore, the use of computer technology is very useful for detecting and consequently mitigating this kind of cyber attacks. Thus, this paper proposes the use of a state-of-the-art model for detecting political-related hate speech on social media. We used three datasets with a significant lexical distance between them. The datasets are in English, Italian, and Filipino languages. To detect hate speech, we propose the use of a PreTrained Language Model (PTLM) with Cross-Lingual Learning (CLL) along with techniques such as ZeroShot (ZST), Joint Learning (JL), Cascade Learning (CL), and CL/JL+. We achieved 94.3% in the F-Score metric using CL/JL+ strategy with the Italian and Filipino datasets as the source language and the English dataset as the target language.

Paper Citation

in Harvard Style

de Oliveira A., Baptista C., Firmino A. and Cardoso de Paiva A. (2023). Using Multilingual Approach in Cross-Lingual Transfer Learning to Improve Hate Speech Detection. In Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS, ISBN 978-989-758-648-4, SciTePress, pages 374-384. DOI: 10.5220/0011851800003467

in Bibtex Style

@conference{iceis23,
author={Aillkeen de Oliveira and Cláudio Baptista and Anderson Firmino and Anselmo Cardoso de Paiva},
title={Using Multilingual Approach in Cross-Lingual Transfer Learning to Improve Hate Speech Detection},
booktitle={Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS,},
year={2023},
pages={374-384},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011851800003467},
isbn={978-989-758-648-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS,
TI - Using Multilingual Approach in Cross-Lingual Transfer Learning to Improve Hate Speech Detection
SN - 978-989-758-648-4
AU - de Oliveira A.
AU - Baptista C.
AU - Firmino A.
AU - Cardoso de Paiva A.
PY - 2023
SP - 374
EP - 384
DO - 10.5220/0011851800003467
PB - SciTePress