Text sentiment classification method, device, electronic device and readable storage medium

Abstract

The embodiment of the present application provides a text sentiment classification method, device, electronic equipment and readable storage medium, the method includes: obtaining the target word vector corresponding to the target keyword in the target text to be classified; passing the first Bi-LSTM layer Extract the syntactic feature of the target word vector, and output the target syntactic feature vector representing the syntactic feature; extract the semantic features of the target syntactic feature vector through the second Bi-LSTM layer, and output the target semantic feature vector representing the semantic feature; through classification The layer determines the sentiment category corresponding to the target text based on the target word vector, the target syntactic feature vector and the target semantic feature vector. Since the syntactic features and semantic features of the target keywords can be extracted in this application, the obtained information can be more comprehensive, and the inner meaning of the target text can be understood more deeply, so the accuracy of the classification results can be effectively improved.

Description

technical field [0001] The present application relates to the technical field of language understanding, and in particular, relates to a text emotion classification method, device, electronic equipment and readable storage medium. Background technique [0002] With the rapid development of Internet technology, more and more users like to publish their opinions, attitudes and opinions on social platforms, thus generating a large number of users' valuable text information on hot events and products on the Internet. These text information contain rich emotional colors and emotional tendencies of users. The purpose of sentiment analysis is to automatically extract and classify users' subjective emotional information from texts to understand the public's views on a certain event or product. [0003] At present, the machine learning method is generally used to identify the emotional category of the text. It usually inputs the relevant features of the extracted text into the classi...

AI Technical Summary

Problems solved by technology

[0004] In view of this, the purpose of the embodiments of the present application is to provide a text sentiment classification method, device, electronic equipment and readable storage medium, so as to improve the problem of low accuracy of text sentiment category classification in the prior art

Images