Cyberbullying can be delineated as a purposive and recurrent act, which is aggressive in nature, done via different social media platforms such as Facebook, Twitter, Instagram, and others. A state-of-the-art pre-training language model, BERT (Bidirectional Encoder Representations from Transformers), has achieved remarkable results in many language understanding tasks. In this paper, we present a novel application of BERT for cyberbullying identification. A straightforward classification model using BERT is able to achieve the state-of-the-art results across three real-world corpora: Formspring ( $$\sim 12\hbox {k}$$ posts), Twitter ( $$\sim 16\hbox {k}$$ posts), and Wikipedia ( $$\sim 100\hbox {k}$$ posts). Experimental results demonstrate that our proposed model achieves significant improvements over existing works, in comparison with the slot-gated or attention-based deep neural network models.

中文翻译：

---

Cyber​​BERT：用于网络欺凌识别的 BERT

网络欺凌可以被描述为一种有目的的、经常性的行为，这种行为本质上是侵略性的，通过 Facebook、Twitter、Instagram 等不同的社交媒体平台进行。最先进的预训练语言模型 BERT（来自 Transformers 的双向编码器表示）在许多语言理解任务中取得了显著成果。在本文中，我们提出了 BERT 用于网络欺凌识别的新应用。使用 BERT 的简单分类模型能够在三个真实世界语料库中获得最先进的结果：Formspring ( $$\sim 12\hbox {k}$$ posts)、Twitter ( $$\sim 16 \hbox {k}$$ 帖子）和维基百科（ $$\sim 100\hbox {k}$$ 帖子）。实验结果表明，我们提出的模型比现有工作取得了显着的改进，