Text emotion recognition method based on maximum probability filling and multi-head attention mechanism

Abstract

The invention discloses a text emotion recognition method based on LDA maximum probability filling and a multi-head attention mechanism, and the method comprises the following steps: (1) obtaining a text data set, and carrying out the text preprocessing; (2) obtaining a dictionary and a word vector matrix through a Word2Vec model; (3) filling a word vector matrix by using an LDA maximum probability method; and (4) mining local features of the text through a Text-CNN network convolution operation, carrying out weight redistribution through a multi-head attention mechanism, and finally obtaining a classification probability of emotional polarity through Softmax. The method can better adapt to the classification task of the network emotion text with flexible length, not only can fully solve the problems of short text data sparseness and filling, but also can cope with the difficulty of long text information extraction.

Description

technical field [0001] The invention relates to a text emotion classification method based on LDA maximum probability filling and multi-head attention mechanism, and belongs to the technical field of text data recognition. Background technique [0002] With the development of Internet technology and the arrival of the era of big data, people are more inclined to express their true opinions on online platforms, and the amount of emotional information such as instant chat, current affairs reviews, and product reviews has grown rapidly. The sentiment classification of these texts has high application value, and can provide support for decision-making judgment, public opinion guidance, recommendation system and other directions. At the same time, these online platform texts will have the characteristics of flexible length and simple grammatical structure, which greatly increases the difficulty of discrimination. Therefore, obtaining short text feature information and improving ...

AI Technical Summary

Problems solved by technology

However, due to the different lengths of the input text, it is necessary to fill the matrix to make the length consistent during batch operations. The mainstream filling methods such as zero-filling and looping will cause data sparseness and semantic confusion.

Images