LSTM-CNN online comment emotion classification method and system based on background enhancement

The invention discloses an LSTM-CNN online comment sentiment classification method and system based on background enhancement, and the method comprises the steps: carrying out the word conversion of a preprocessed online comment text, obtaining the word vector representation of the online comment text, extracting the features of a news text through a TF-IDF algorithm fusing the part-of-speech and position information, and carrying out the recognition of the features of the news text; extracting local features of a comment text by using a convolutional neural network, splicing news text features obtained by a news text feature extraction channel and comment text features obtained by an online comment text feature extraction channel to obtain a comment text feature vector based on background enhancement, and taking the comment text as a language background; the method comprises the following steps: extracting a news text feature, taking the news text feature as a comment text sentiment analysis feature, adding