用数据增强提升大模型检测仇恨言论能力，发现不同方法效果因数据和模型而异。
Hate Speech Detection using Large Language Models with Data Augmentation and Feature Enhancement
- 结合数据增强与特征强化，测试多种模型在不同数据集上的表现。
- gpt-oss-20b表现最优，Delta TF-IDF经增强后达98.2%准确率。
- 隐性仇恨言论更难识别，方法效果依赖数据、模型与技术的协同。
本文评估了数据增强与特征增强技术在仇恨言论检测中的作用，对比了传统分类器（如Delta TF-IDF）与基于Transformer的模型（DistilBERT、RoBERTa、DeBERTa、Gemma-7B、gpt-oss-20b）在多个数据集上的表现。研究考察了合成少数类过采样技术（SMOTE）、基于类别逆比例的加权损失、词性标注（POS）以及文本数据增强对模型性能的影响。开源模型gpt-oss-20b始终表现最佳。另一方面，Delta TF-IDF在数据增强后于Stormfront数据集达到98.2%准确率。研究确认隐性仇恨言论比显性内容更难检测，且增强效果取决于数据集、模型与技术的相互作用。本研究揭示了数据特性、模型架构与增强策略间的复杂关系，为构建更精准、上下文感知的自动化仇恨言论检测系统提供依据。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。