News text classification based on hybrid model of Bidirectional Encoder Representation from Transformers and Convolutional Neural Network

Abstract

At present, with the rapid development of Internet technology, text data show massive characteristics. Network media and new media platforms have become an important part of journalism and communication, and network news has become one of the important sources of information. In order to meet the needs of online news reading users and improve the efficiency of personalized news recommendation by content distribution platform, it is urgent to effectively manage and utilize online news. Based on this, this paper studies and implements the algorithm for news text classification, and the goal is to build a classification model for news text with higher classification accuracy. In this paper, BERT and CNN algorithm are combined to classify news texts. The core idea is to send BERT as the embedding layer into the CNN model. The experimental results show that this method is better than the simple BERT model or the simple CNN model.