Network Pornographic Information Identification Based on Improved Random Forest

The rapid spread of network pornographic information in the era of generative artificial intelligence has led to frequent happening of crimes. In order to effectively discover harmful information, we propose a network pornographic information identification approach using improved random forest algorithm based on text content. Firstly, according to special characteristics of pornographic information, key features are extracted by means of the preprocessing process and the term important method. Secondly, an improved random forest algorithm is designed to build a prediction model for identifying pornographic information. Finally, experimental results show that the proposed approach is superior to other classic approaches in terms of performance and run time.