Evaluation text analysis method and device and computer readable storage medium

Abstract

The invention discloses an evaluation text analysis method and device and a computer readable storage medium, and relates to the field of natural language process.The method comprises the steps that a to-be-processed text is obtained, evaluation statements in the to-be-processed text are preprocessed, and a word identification sequence is obtained, based on a pre-trained word embedding vector matrix and / or an auxiliary embedding vector matrix, mapping the word identification sequence into a word vector matrix, inputting the word vector matrix into a preset expansion loop convolutional neural network model to obtain convolutional features, and fusing a correlation matrix obtained by pre-analysis into the convolutional features to obtain fused features, and performing linear mapping on the fusion features to obtain an estimated score matrix of the expansion cycle convolutional neural network model for each word tag, and analyzing tag information of each evaluation statement in the to-be-processed text. According to the method and the device, the technical problem that fine-grained analysis cannot be performed on the tendency opinions of the evaluation object in the evaluation statement in the prior art is solved.

Description

technical field [0001] The present invention relates to the technical field of analysis, in particular to an analysis method for evaluating text, a device thereof, and a computer-readable storage medium. Background technique [0002] With the development of emerging social media, users can publish personal content in the form of text, pictures, videos, etc. for information exchange and expression of opinions. Analyzing these massive user-generated data will help to obtain various information. The current analysis method is mainly text-oriented, and through the analysis of the text, the opinions and attitudes of commentators on things or events are discovered. In the research of natural language processing, sentiment analysis is a common task, which mainly analyzes text-level, sentence-level and object-level tasks. For example, in the user product review module of an e-commerce platform, users can target The purchased products are evaluated, and the review rating classificat...

AI Technical Summary

Problems solved by technology

[0006] Embodiments of the present invention provide an evaluation text analysis method, its device, and a computer-readable storage medium, so as to at least solve the technical problem in the related art that it is impossible to make fine-grained analysis of the tendencies of evaluation objects in evaluation sentences

Images