Chinese Sentiment Classification Model of Neural Network Based on Particle Swarm Optimization

Due to the differences in features between different languages, Chinese text is more complicated and difficult in natural language processing tasks than English text. This paper proposes a neural network Chinese sentiment classification model based on particle swarm optimization (PSO-Attention-LSTM), the model uses the Long Short Term Memory Network superimposed attention mechanism to extract information from Chinese review data and determine the sentiment polarity of the sentence; aiming at the problem that parameters such as the number of hidden layer neurons in the LSTM unit and the number of batches of the neural network are difficult to determine, the global optimization capability of the particle swarm optimization (PSO) is used to optimize the parameters. The experimental results show that the neural network Chinese sentiment classification model based on particle swarm optimization has improved the accuracy of the hotel data set by nearly 6 percentage points.