A Large-scale Dataset for Hate Speech Detection on Vietnamese Social Media Texts

TL;DR

This paper introduces ViHSD, a large annotated dataset of Vietnamese social media comments labeled for hate speech, enabling improved automatic detection using deep learning and transformer models.

Contribution

The paper presents a new large-scale, human-annotated Vietnamese hate speech dataset and details its creation and evaluation process.

Findings

Deep learning models achieved high accuracy on the dataset

Transformer models outperformed traditional methods

The dataset facilitates future hate speech detection research in Vietnamese

Abstract

In recent years, Vietnam witnesses the mass development of social network users on different social platforms such as Facebook, Youtube, Instagram, and Tiktok. On social medias, hate speech has become a critical problem for social network users. To solve this problem, we introduce the ViHSD - a human-annotated dataset for automatically detecting hate speech on the social network. This dataset contains over 30,000 comments, each comment in the dataset has one of three labels: CLEAN, OFFENSIVE, or HATE. Besides, we introduce the data creation process for annotating and evaluating the quality of the dataset. Finally, we evaluated the dataset by deep learning models and transformer models.