A Text Sentiment Classification Algorithm Based on Convolutional Neural Network and Attention Mechanism

Abstract

The invention discloses a text emotion classification algorithm based on a convolutional neural network and an attention mechanism. One model; 2) Establish a multi-head dot product attention mechanism with residual connection and nonlinearity, and use sentiment classification text for training to obtain the second model; 3) Model fusion of the two models to obtain text sentiment classification . The present invention integrates multiple granularities, multiple convolutions, and multiple pools into the convolutional neural network, introduces residual connections and nonlinearity into the attention mechanism, and calculates multiple attentions to obtain two text emotion classification models, Through the Bagging model fusion method, the fusion model is obtained, and the text is classified, which can combine the advantages of the convolutional neural network to better capture local features and the attention mechanism to better capture global information, and obtain a more comprehensive text emotion classification model.

Description

technical field [0001] The invention relates to the field of text classification of natural language processing, in particular to a text emotion classification algorithm based on a convolutional neural network and an attention mechanism. Background technique [0002] Text classification has various applications, such as sentiment polarity classification, topic classification, etc. For text classification, there are many commonly used methods, such as unsupervised methods based on dictionaries and rules, and supervised methods based on machine learning. The dictionary-based method uses authoritative dictionaries and artificially constructs features according to experience. The accuracy of the model is high, but the recall rate of the model is low due to the low coverage of the dictionary. Supervised methods based on machine learning, modeled using machine learning methods such as SVM, maximum entropy model, naive Bayesian, and KNN. These machine learning methods are relativ...

AI Technical Summary

Problems solved by technology

However, ordinary convolutional neural networks set fixed filters and pooling operation types, and the captured local information has a fixed granularity, is relatively rigid, and lacks diversity.

Images