用多源词向量+注意力机制提升阿尔及利亚方言仇恨言论检测效果
FAD-SA-GRU: Enhancing Hate Speech Detection in Algerian Dialect Through Feature-Augmented Self-Attention GRU Networks
- 融合DZ FastText、DZ AraVec和DziriBERT三类词向量，增强语义表征
- 在阿尔及利亚方言数据集上达到93.2%准确率，显著优于传统模型
- 适合低资源阿拉伯方言文本分析，对内容审核系统有实用价值
社交媒体的普及改变了在线交流方式，但也加速了攻击性与仇恨内容的传播，带来社会、心理与伦理挑战。仇恨言论可能基于种族、宗教、性别、国籍或政治立场引发歧视、骚扰甚至暴力。因此，自动仇恨言论检测成为自然语言处理的重要课题，也是内容审核的关键环节。本文研究阿尔及利亚阿拉伯语（Darija）社交媒体中的自动仇恨言论检测。该任务因方言语言多样性而困难，其特点为阿拉伯语、法语与阿拉伯拉丁化拼写（Arabizi）共存。我们比较四类文本分类方法：(1) 基于TF-IDF的传统机器学习模型，(2) 循环神经网络深度学习模型，(3) Transformer类语言模型（包括DziriBERT和多语言BERT），(4) 一种新型混合架构FAD-SA-GRU，通过多嵌入融合整合DZ FastText、DZ AraVec和DziriBERT的语义表示，再经自注意力增强的GRU编码器处理。在标注的阿尔及利亚阿拉伯语社交媒体评论二分类数据集上的实验表明，FAD-SA-GRU优于所有基线模型，达93.2%准确率、93.4%精确率、91.0%召回率、92.1% F1分数与97.0% ROC-AUC。结果证明，结合互补嵌入表示与基于注意力的序列建模，可有效提升低资源阿拉伯方言仇恨言论检测性能。
原文摘要 · Abstract (English)
The widespread adoption of social media platforms has transformed online communication by enabling users to exchange information and opinions instantly. However, these platforms have also facilitated the dissemination of abusive and hateful content, posing major social, psychological, and ethical challenges. Hate speech can incite discrimination, harassment, and violence against individuals or communities based on attributes such as ethnicity, religion, gender, nationality, or political affiliation. Consequently, automatic hate speech detection has become a major research topic in natural language processing (NLP) and an essential component of content moderation systems. This paper investigates automatic hate speech detection in the Algerian Arabic dialect (Darija) on social media. This task remains challenging because of the dialect's linguistic diversity, characterized by the coexistence of Arabic, French, and Arabizi (Arabic written using the Latin alphabet). We compare four categories of text classification approaches: (1) traditional machine learning models using TF-IDF features, (2) deep learning models based on recurrent neural networks, (3) Transformer-based language models, including DziriBERT and multilingual BERT, and (4) a novel hybrid architecture, FAD-SA-GRU, which combines semantic representations from DZ FastText, DZ AraVec, and DziriBERT through multi-embedding fusion, followed by a self-attention-enhanced GRU encoder. Experiments on an annotated dataset of Algerian Darija social media comments for binary hate speech classification show that FAD-SA-GRU outperforms all baselines, achieving 93.2% accuracy, 93.4% precision, 91.0% recall, 92.1% F1-score, and 97.0% ROC-AUC. Results demonstrate the effectiveness of combining complementary embedding representations with attention-based sequence modeling for robust hate speech detection in low-resource dialectal Arabic.
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。