关键词: 网络欺凌检测, 深度学习, 迁移学习, ELMo模型, TextCNN模型

Abstract: Cyberbullying detection is an important research content on cyberspace information content security, and it is also related to youth online security. Aiming at the problems of few training samples, difficulty in processing polysemous words and unsatisfactory classification performance in current cyberbullying detection schemes, an ELMoTextCNN detection model is proposed. The model first adopts the idea of transfer learning and uses pretrained embeddings from language models (ELMo) to generate dynamic word vectors, which not only solves the problem of small cyberbullying sample size, but also because ELMo uses the bidirectional long shortterm memory (BiLSTM) network structure, it will infer the word vector corresponding to each word based on the context, and can understand polysemous words according to context. The model extracts text features through a text convolutional neural network (TextCNN), which is good at processing short text data, and finally outputs the classification results through a fully connected layer. Experimental results prove that the proposed ELMoTextCNN detection method can handle the ambiguity of a word and obtain better classification and detection results.

Key words: cyberbullying detection;deep learning, transfer learning ;ELMo model, TextCNN model