Text sentiment analysis method based on deep learning

Abstract

The invention provides a text sentiment analysis method based on deep learning. The method comprises the following steps: (1) inputting text data, removing stop words, and extracting keywords to forma keyword set; (2) forming a dense sub-graph by constructing a keyword co-occurrence graph; vector representations of sentences in the sub-graphs and the document are obtained, and then the sentencesare distributed to the sub-graphs; designing edge connection and edge weight between the sub-graphs to form topological interaction graph expression of the document; and (3) taking the topological interaction diagram as the input of an Emo-GCN model, carrying out node feature extraction transformation, and then fusing local structure information to obtain a node aggregation matrix. The nonlinear transformation is carried out on the aggregated information. The Emo-GCN model adopts a hierarchical structure, and the features are extracted layer by layer. According to the method, the novel topological interaction graph is adopted to express the text information, then the graph convolutional neural network is used for text sentiment analysis, and the method still has strong adaptability. The method is applied to product recommendation, market prediction and decision adjustment, and has extremely high commercial value.

Description

technical field [0001] The present invention relates to a natural language processing method, and also relates to an image classification method, specifically a text sentiment analysis method. Background technique [0002] Text classification is a classic problem in the field of natural language processing, and emotion recognition is a challenging task in text classification. Currently, there are three main methods for dealing with the problem of sentiment analysis: one is to construct a sentiment dictionary for sentiment analysis. The construction of vocabulary into an emotional dictionary is a necessary but not sufficient condition for sentiment analysis. No matter how the content of the emotional dictionary is expanded, it cannot contain all forms of emotional expression. In addition, the emotional polarity of some words is not clear, and some sentences may not use emotional words. , but it also expresses a certain emotion, and some emotional words express the exact oppos...

AI Technical Summary

Problems solved by technology

But in real life, most of the data has an irregular structure. This kind of data will be expressed by a topological interaction graph, which does not have translation invariance. It is difficult to choose a fixed convolution kernel to adapt to the irregularity of the entire graph. The data of this structure will cause CNN or RNN to fail instantly

Images