Sentiment Analysis of Movie Review Based on LSTM

Abstract

This paper introduces a sentiment analysis model based on LSTM (Long Short-Term Memory), which can be used for emotional polarity classification of movie review data. The model consists of five levels, namely input layer, embedding layer, LSTM layer, softmax layer, and output layer. IMDb (Internet Movie Database) dataset is used for training, and SGD (stochastic gradient descent), Adadelta, and RMSprop for optimization. The experiment result shows that Adadelta optimization algorithm can get the best training model and the lowest prediction error rate.