Hate Speech Detection using Large Language Models with Data Augmentation and Feature Enhancement

TL;DR

This study compares traditional and transformer-based models for hate speech detection, demonstrating how data augmentation and feature enhancement techniques influence performance across various datasets and models.

Contribution

It introduces a comprehensive evaluation of data augmentation and feature enhancement methods for hate speech detection using both traditional and transformer models.

Findings

gpt-oss-20b achieves highest accuracy among models

Delta TF-IDF responds strongly to data augmentation, reaching 98.2% accuracy

Implicit hate speech detection remains more challenging than explicit content

Abstract

This paper evaluates data augmentation and feature enhancement techniques for hate speech detection, comparing traditional classifiers, e.g., Delta Term Frequency-Inverse Document Frequency (Delta TF-IDF), with transformer-based models (DistilBERT, RoBERTa, DeBERTa, Gemma-7B, gpt-oss-20b) across diverse datasets. It examines the impact of Synthetic Minority Over-sampling Technique (SMOTE), weighted loss determined by inverse class proportions, Part-of-Speech (POS) tagging, and text data augmentation on model performance. The open-source gpt-oss-20b consistently achieves the highest results. On the other hand, Delta TF-IDF responds strongly to data augmentation, reaching 98.2% accuracy on the Stormfront dataset. The study confirms that implicit hate speech is more difficult to detect than explicit hateful content and that enhancement effectiveness depends on dataset, model, and technique interaction. Our research informs the development of hate speech detection by highlighting how dataset properties, model architectures, and enhancement strategies interact, supporting more accurate and context-aware automated detection.