Research on the Design of News Text Classification Algorithm Based on Bidirectional GRU Neural Network

This study addresses the growing demand for news text classification driven by the rapid expansion of internet information by proposing a classification algorithm based on a Bidirectional Gated Recurrent Unit (BiGRU) neural network to enhance classification accuracy and efficiency.Traditional text classification methods often suffer from inefficiency and insufficient accuracy when handling large-scale news data, whereas the application of deep learning techniques provides a novel approach to improving text classification.The proposed algorithm first preprocesses news texts through tokenization, stop-word removal, and low-frequency word filtering to optimize text representation.Subsequently, the BiGRU model is employed for feature extraction and classification.Experimental results demonstrate that the model achieves an accuracy of over 90% across 11 news categories, with an average classification time per news item of less than five seconds, indicating strong classification performance and computational efficiency.This study offers an effective solution for automated news classification on news platforms and holds significant potential for broader applications.