Graphical Visual Analysis of Consumer Electronics Public Comment Information Mining Under Knowledge Graph

With the continuous development of information technology, information in electronic products has shown explosive growth. Data mining for these reviews can better visualize them. To find the information you need quickly and accurately from the vast amount of information, this paper analyzes the algo...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on consumer electronics Vol. 70; no. 1; pp. 2917 - 2924
Main Authors: Yi, Guohong, Wu, Shaofei
Format: Journal Article
Language:English
Published: New York IEEE 01.02.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Classification
Consumer electronics
Convolution
convolutional neural network
Convolutional neural networks
Data mining
Data visualization
Datasets
Electronics
Feature extraction
graph convolutional network
information sentiment visualization
Knowledge
knowledge graph
Knowledge graphs
Knowledge representation
Model accuracy
Sentiment visualization
Visualization
ISSN:0098-3063, 1558-4127
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:With the continuous development of information technology, information in electronic products has shown explosive growth. Data mining for these reviews can better visualize them. To find the information you need quickly and accurately from the vast amount of information, this paper analyzes the algorithm process of commenting on the information sentiment visualization from the theoretical knowledge of Knowledge Graph and information sentiment visualization to quickly and accurately find the required information from the massive information. The knowledge classification model based on Graph Convolution Network (GCN) is discussed. A visual analysis model of comment information sentiment is constructed based on the Knowledge Graph GCN classification model. The model's performance is verified by the comparison experiment of the Relation-GCN (R-GCN) classification experiment and link prediction under different datasets. The results show that in analyzing the mobile comments of a shopping website, the sentiment visualization of the comment information can help users decide whether to buy consumer electronics. According to the entity classification dataset, the accuracy of the model constructed here has reached 80%. In addition, the associated prediction data sets are comparatively analyzed. It is found that the R-GCN model is significantly better than the GCN model, and its Mean Reciprocal Ranking is at least 14.6% higher than that of the GCN model. Therefore, the visualization of comment information based on the Knowledge Graph here can provide new ideas for the collation of comment information and the construction of the Knowledge Graph.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0098-3063
1558-4127
DOI:10.1109/TCE.2023.3300534