信息安全研究2025，Vol.11Issue(2)：154-163,10.DOI:10.12379/j.issn.2096-1057.2025.02.08
面向社交网络平台的多模态网络欺凌检测模型研究
Research on Multi-modal Cyberbullying Detection Model for Social Networking Platforms
摘要
Abstract
With the rapid development of social networking platforms,the issue of cyberbullying has become increasingly prominent.The diverse forms of online expression that combine text and images have increased the difficulty of detecting and managing cyberbullying.This paper constructs a Chinese multi-modal cyberbullying dataset that includes both text and images.By integrating the BERT(bidirectional encoder representations from transformers)model with the ResNet50 model,we extract single-modal features from text and images,respectively,and perform decision-level fusion.The fused features are then detected,achieving accurate identification of text and images as either cyberbullying or non-cyberbullying.Experimental results indicate that the multi-modal cyberbullying detection model proposed in this paper can effectively identify social media posts or comments that contain cyberbullying characteristics in both text and images.It enhances the practicality,accuracy,and efficiency of detecting multi-modal cyberbullying,providing a new approach and method for the detection and management of cyberbullying on social networking platforms.This contributes to the creation of a healthier and more civilized online environment.关键词
网络欺凌/多模态/特征融合/检测模型/社交网络平台Key words
cyberbullying/multi-modal/feature fusion/detection model/social network platforms分类
信息技术与安全科学引用本文复制引用
李猛坤,李柯锦,王琪,袁晨,吕慧颖,应作斌..面向社交网络平台的多模态网络欺凌检测模型研究[J].信息安全研究,2025,11(2):154-163,10.基金项目
北京市社会科学基金重点项目(24LLGAB046) （24LLGAB046）
