Deep learning-driven sensitive word recognition method
TL;DR
This article reviews deep learning-based sensitive word recognition methods from three categories: Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Graph Neural Network (GNN), and summarizes the classic public data sets in this field.
Abstract
With the rapid development of social media, a large number of users' comments are constantly generated in the network, and some harmful content containing sensitive information seriously affects the network environment. The development of deep learning has promoted research and governance in this field. This article reviews deep learning-based sensitive word recognition methods from three categories: Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Graph Neural Network (GNN), and summarizes the classic public data sets in this field. In addition, it also points out the characteristics of each method and the problems to be solved in this field, such as the lack of public data resources, the weakness of multimodal comprehensive analysis, and the dialect bias of the model. This article aims to systematically review the research progress in the field of sensitive word recognition, summarize the applicable scenarios and limitations of different deep learning methods, and provide useful references for subsequent research.