News classifications based on CBA-PreambleCNN Model

In order to solve the problems of insufficient information extraction and poor classification effect of a single deep learning model, this paper proposes a hybrid multi-neural network CBOW-BiLSTM-Attention-PreambleCNN model(The CBA-PreambleCNN for short, PreambleCNN is the name of the improved TextCNN). The model uses Word2Vec as the word embedding layer to obtain the vector representation of the word, and then feeds the Bidirectional Long Short-Term Memory (BI-LSTM) network to capture the global information of the text, and then uses the Attention mechanism to make the word get different weights. Finally, it is fed into the improved Text Convolutional Neural Network (TextCNN fused with previous information, named PreambleCNN) to obtain the topic features of the Text, and the obtained feature vectors are fed into the softmax function for classification. After comparison with other models, this model has achieved good classification effect, and achieved 93.47% and 84.65% accuracy on Sina news dataset and Sohu news dataset, respectively. To some extent, this model solves the problem of insufficient information captured by a single model.