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

• URL: http://arxiv.org/abs/2603.04698v1
• Date: Thu, 05 Mar 2026 00:46:11 GMT
• Title: Hate Speech Detection using Large Language Models with Data Augmentation and Feature Enhancement
• Authors: Brian Jing Hong Nge, Stefan Su, Thanh Thi Nguyen, Campbell Wilson, Alexandra Phelan, Naomi Pfitzner,
• Abstract summary: This paper evaluates data augmentation and feature enhancement techniques for hate speech detection.<n>It examines the impact ofSMOTE, weighted loss determined by inverse class proportions, Part-of-Speech (POS) tagging, and text data augmentation on model performance.
• Score: 37.96170496349076
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• AI Generated Text Detection [0.0]
  This paper presents an evaluation of AI text detection methods, including both traditional machine learning models and transformer-based architectures.<n>We utilize two datasets, HC3 and DAIGT v2, to build a unified benchmark and apply a topic-based data split to prevent information leakage.<n>Results indicate that contextual modeling is significantly superior to lexical features and highlight the importance of mitigating topic memorization.
  arXiv  Detail & Related papers  (2026-01-07T11:18:10Z)
• Explicit and Implicit Data Augmentation for Social Event Detection [61.929049997741735]
  Social event detection involves identifying and categorizing important events from social media.<n>We propose Augmentation framework for Social Event Detection (SED-Aug)<n>SED-Aug combines explicit text-based and implicit feature-space augmentation to enhance data diversity and model robustness.
  arXiv  Detail & Related papers  (2025-09-04T13:26:24Z)
• Discourse Features Enhance Detection of Document-Level Machine-Generated Content [53.41994768824785]
  Machine-generated content poses challenges such as academic plagiarism and the spread of misinformation.<n>Existing MGC detectors often focus solely on surface-level information, overlooking implicit and structural features.<n>We introduce novel methodologies and datasets to overcome these challenges.
  arXiv  Detail & Related papers  (2024-12-17T08:47:41Z)
• A Target-Aware Analysis of Data Augmentation for Hate Speech Detection [3.858155067958448]
  Hate speech is one of the main threats posed by the widespread use of social networks. We investigate the possibility of augmenting existing data with generative language models, reducing target imbalance. For some hate categories such as origin, religion, and disability, hate speech classification using augmented data for training improves by more than 10% F1 over the no augmentation baseline.
  arXiv  Detail & Related papers  (2024-10-10T15:46:27Z)
• Improving Sampling Methods for Fine-tuning SentenceBERT in Text Streams [49.3179290313959]
  This study explores the efficacy of seven text sampling methods designed to selectively fine-tune language models. We precisely assess the impact of these methods on fine-tuning the SBERT model using four different loss functions. Our findings indicate that Softmax loss and Batch All Triplets loss are particularly effective for text stream classification.
  arXiv  Detail & Related papers  (2024-03-18T23:41:52Z)
• Robust Hate Speech Detection in Social Media: A Cross-Dataset Empirical Evaluation [5.16706940452805]
  We perform a large-scale cross-dataset comparison where we fine-tune language models on different hate speech detection datasets. This analysis shows how some datasets are more generalisable than others when used as training data. Experiments show how combining hate speech detection datasets can contribute to the development of robust hate speech detection models.
  arXiv  Detail & Related papers  (2023-07-04T12:22:40Z)
• Hate Speech and Offensive Language Detection using an Emotion-aware Shared Encoder [1.8734449181723825]
  Existing works on hate speech and offensive language detection produce promising results based on pre-trained transformer models. This paper addresses a multi-task joint learning approach which combines external emotional features extracted from another corpora. Our findings demonstrate that emotional knowledge helps to more reliably identify hate speech and offensive language across datasets.
  arXiv  Detail & Related papers  (2023-02-17T09:31:06Z)
• Deep Learning for Hate Speech Detection: A Comparative Study [54.42226495344908]
  We present here a large-scale empirical comparison of deep and shallow hate-speech detection methods. Our goal is to illuminate progress in the area, and identify strengths and weaknesses in the current state-of-the-art. In doing so we aim to provide guidance as to the use of hate-speech detection in practice, quantify the state-of-the-art, and identify future research directions.
  arXiv  Detail & Related papers  (2022-02-19T03:48:20Z)
• AES Systems Are Both Overstable And Oversensitive: Explaining Why And Proposing Defenses [66.49753193098356]
  We investigate the reason behind the surprising adversarial brittleness of scoring models. Our results indicate that autoscoring models, despite getting trained as "end-to-end" models, behave like bag-of-words models. We propose detection-based protection models that can detect oversensitivity and overstability causing samples with high accuracies.
  arXiv  Detail & Related papers  (2021-09-24T03:49:38Z)
• Improved Speech Emotion Recognition using Transfer Learning and Spectrogram Augmentation [56.264157127549446]
  Speech emotion recognition (SER) is a challenging task that plays a crucial role in natural human-computer interaction. One of the main challenges in SER is data scarcity. We propose a transfer learning strategy combined with spectrogram augmentation.
  arXiv  Detail & Related papers  (2021-08-05T10:39:39Z)
• Statistical Analysis of Perspective Scores on Hate Speech Detection [7.447951461558536]
  State-of-the-art hate speech classifiers are efficient only when tested on the data with the same feature distribution as training data. In such a diverse data distribution relying on low level features is the main cause of deficiency due to natural bias in data. We show that, different hate speech datasets are very similar when it comes to extract their Perspective Scores.
  arXiv  Detail & Related papers  (2021-06-22T17:17:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.