LSTM Based on the Classification of Emotion about User Evaluation on Shopping Site

Abstract

The user evaluation of shopping websites always has huge amounts of data which is a waste of manpower and material resources. Aiming at this problem, this paper puts forward a model based on LSTM and word vectors [1]. LSTM can be a very good solution because of the long distance learning of the neural nodes to forward neural nodes of declining awareness, thus LSTM neural network model can be better to finish the task of user sentiment analysis.