摘要：Deep learning is used to deal with natural language processing problems. Some are based on phrases and some are based on words. This article is inspired by the pixel level in the CV world and therefore retrains the neural network from a character perspective. Neural networks do not need to know about word lookup table or word2vec in advance, and the knowledge of these words is often high-dimensional and it is difficult to apply to convolutional neural networks. In addition, our long-short term memory convolutional neural networks no longer need to know the syntax and semantics in advance. The purpose of this paper is to analyse the investor's psychological characteristics and investment decision-making behaviour characteristics, to study the investor sentiment in the network public opinion space.
