Quality analysis method and device of comment data, electronic equipment and storage medium

Abstract

The invention discloses a comment data quality analysis method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining target comment data to be subjected to quality analysis; analyzing the comment contents and the comment phrases to obtain a comment theme corresponding to the target comment data, and obtaining an association relationship set among the comment theme, the comment contents and the comment phrases; generating an initial graph structure based on the comment contents, the comment phrases, the comment themes and the association relationship set, and converting the comment contents, the comment themes and the comment phrases in the initial graph structure into corresponding initial embedded matrixes to obtain a target graph structure; and inputting the target graph structure into a pre-trained graph attention model to obtain a quality analysis result of the target comment data. According to the method, the graph structure is generated by establishing the relation among the theme, the content and the word group, so that the comments are completely covered, meanwhile, feature analysis is performed on the graph structure based on the graph attention model, and the accuracy of comment quality analysis is improved.

Description

technical field [0001] The present application relates to the field of data processing, in particular to a quality analysis method, device, electronic equipment and storage medium for review data. Background technique [0002] With the rapid development of the Internet, user comment data on the Internet has increased significantly, and analyzing the quality of comments has become more and more important for user tendencies, public opinion control, and precision marketing. In recent years, Graph Neural Network (GraphNeural Network, GNN) began to develop. The emergence of GNN has realized the end-to-end learning method of graph data, making the learning process directly built on graph data. It can better capture the overall structural characteristics of the network, and has better representation and reasoning capabilities than traditional deep learning frameworks. [0003] In the research on text classification in recent years, such as analyzing the quality of comment data, ...

AI Technical Summary

Problems solved by technology

Based on this, the inventors found that word nodes and document nodes are respectively represented as two types of nodes in the figure, which cannot fully cover the comment data, and ultimately lead to inaccurate analysis results of comment quality

Images