Hate Speech Detection using Large Language Models with Data Augmentation and Feature Enhancement
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908867244326912 |
|---|---|
| author | Nge, Brian Jing Hong Su, Stefan Nguyen, Thanh Thi Wilson, Campbell Phelan, Alexandra Pfitzner, Naomi |
| author_facet | Nge, Brian Jing Hong Su, Stefan Nguyen, Thanh Thi Wilson, Campbell Phelan, Alexandra Pfitzner, Naomi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_04698 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Hate Speech Detection using Large Language Models with Data Augmentation and Feature Enhancement Nge, Brian Jing Hong Su, Stefan Nguyen, Thanh Thi Wilson, Campbell Phelan, Alexandra Pfitzner, Naomi Computation and Language Artificial Intelligence 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. |
| title | Hate Speech Detection using Large Language Models with Data Augmentation and Feature Enhancement |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2603.04698 |