融合用户信息提升仇恨言论检测准确率
A Unified Multi-Task Learning Architecture for Hate Detection Leveraging User-Based Information
- 利用用户内与用户间信息增强文本识别
- 多任务学习下宏平均F1显著提升
- 适合社交平台内容安全系统开发者
仇恨言论、攻击性语言、种族主义、性别歧视等滥用语言在社交媒体中普遍存在，亟需基于人工智能的规模化干预。现有检测方法通常将每条动态视为孤立输入，本文提出一种统一的多任务学习架构，通过引入用户内与用户间信息，提升英语仇恨言论识别效果。实验在CNN、GRU、BERT和ALBERT等深度神经网络上进行，对比单任务学习（STL）与多任务学习（MTL）范式，使用三个基准数据集验证。结果表明，结合特定用户特征与文本特征，在宏平均F1和加权F1上均取得显著提升。
原文摘要 · Abstract (English)
Hate speech, offensive language, aggression, racism, sexism, and other abusive language are common phenomena in social media. There is a need for Artificial Intelligence(AI)based intervention which can filter hate content at scale. Most existing hate speech detection solutions have utilized the features by treating each post as an isolated input instance for the classification. This paper addresses this issue by introducing a unique model that improves hate speech identification for the English language by utilising intra-user and inter-user-based information. The experiment is conducted over single-task learning (STL) and multi-task learning (MTL) paradigms that use deep neural networks, such as convolutional neural networks (CNN), gated recurrent unit (GRU), bidirectional encoder representations from the transformer (BERT), and A Lite BERT (ALBERT). We use three benchmark datasets and conclude that combining certain user features with textual features gives significant improvements in macro-F1 and weighted-F1.
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。