An optimized public opinion communication system in social media networks based on K-means cluster analysis

This study proposes a public opinion monitoring model that combines the K-means clustering algorithm with Particle Swarm Optimization (PSO) to enhance the accuracy and effectiveness of public opinion monitoring on social media. The model's performance across various dissemination indicators is...

Full description

Saved in:
Bibliographic Details
Main Authors: Mingchao Qi, JunQiang Zhao, Yan Feng
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Heliyon
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2405844024160641
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846115982698872832
author Mingchao Qi
JunQiang Zhao
Yan Feng
author_facet Mingchao Qi
JunQiang Zhao
Yan Feng
author_sort Mingchao Qi
collection DOAJ
description This study proposes a public opinion monitoring model that combines the K-means clustering algorithm with Particle Swarm Optimization (PSO) to enhance the accuracy and effectiveness of public opinion monitoring on social media. The model's performance across various dissemination indicators is studied in detail. Through experiments conducted on social media datasets, the study comprehensively evaluates the model from four dimensions: dissemination speed, scope, depth, and sentiment dissemination effectiveness. The experimental results indicate that the proposed optimization model excels in multiple areas, particularly in dissemination depth and sentiment dissemination effectiveness. Specifically, in the three dimensions of dissemination speed, the proposed model achieves scores of 4.3, 4.2, and 4.4 in initial dissemination speed, decay speed, and peak dissemination speed, respectively. In the dimensions of user coverage, geographic coverage, and platform coverage under dissemination scope, the model scores 4.4, 4.5, and 4.3, demonstrating a broad dissemination capability. Additionally, in the dimensions of hierarchical dissemination depth and key node influence within dissemination depth, the model scores 4.3 and 4.5, indicating excellent performance in multi-level dissemination and key node activation. In sentiment dissemination effectiveness, the model receives scores of 4.4, 4.5, and 4.4 in emotional tendency change, polarity distribution, and diffusion intensity, showcasing its advantages in sentiment classification and dissemination. Sensitivity analysis further validates the model's sensitivity to parameter settings, with experiments showing that reasonable adjustments to parameters such as the K value, PSO inertia weight, and learning factors can reduce the Sum of Squared Errors to 3209.72. Meanwhile, it can improve clustering purity to 0.822 and raise the Rand index to 0.623. Therefore, this study offers an efficient and reliable solution for public opinion monitoring on social media, providing valuable reference significance.
format Article
id doaj-art-ca9e4c2e82054d9cbb1e5d9e339e3b51
institution Kabale University
issn 2405-8440
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Heliyon
spelling doaj-art-ca9e4c2e82054d9cbb1e5d9e339e3b512024-12-19T10:55:49ZengElsevierHeliyon2405-84402024-12-011024e40033An optimized public opinion communication system in social media networks based on K-means cluster analysisMingchao Qi0JunQiang Zhao1Yan Feng2Corresponding author.; Xinxiang Medical University, Xinxiang, 453000, ChinaXinxiang Medical University, Xinxiang, 453000, ChinaXinxiang Medical University, Xinxiang, 453000, ChinaThis study proposes a public opinion monitoring model that combines the K-means clustering algorithm with Particle Swarm Optimization (PSO) to enhance the accuracy and effectiveness of public opinion monitoring on social media. The model's performance across various dissemination indicators is studied in detail. Through experiments conducted on social media datasets, the study comprehensively evaluates the model from four dimensions: dissemination speed, scope, depth, and sentiment dissemination effectiveness. The experimental results indicate that the proposed optimization model excels in multiple areas, particularly in dissemination depth and sentiment dissemination effectiveness. Specifically, in the three dimensions of dissemination speed, the proposed model achieves scores of 4.3, 4.2, and 4.4 in initial dissemination speed, decay speed, and peak dissemination speed, respectively. In the dimensions of user coverage, geographic coverage, and platform coverage under dissemination scope, the model scores 4.4, 4.5, and 4.3, demonstrating a broad dissemination capability. Additionally, in the dimensions of hierarchical dissemination depth and key node influence within dissemination depth, the model scores 4.3 and 4.5, indicating excellent performance in multi-level dissemination and key node activation. In sentiment dissemination effectiveness, the model receives scores of 4.4, 4.5, and 4.4 in emotional tendency change, polarity distribution, and diffusion intensity, showcasing its advantages in sentiment classification and dissemination. Sensitivity analysis further validates the model's sensitivity to parameter settings, with experiments showing that reasonable adjustments to parameters such as the K value, PSO inertia weight, and learning factors can reduce the Sum of Squared Errors to 3209.72. Meanwhile, it can improve clustering purity to 0.822 and raise the Rand index to 0.623. Therefore, this study offers an efficient and reliable solution for public opinion monitoring on social media, providing valuable reference significance.http://www.sciencedirect.com/science/article/pii/S2405844024160641Cluster analysisSocial mediaNetwork public opinionData miningK-means algorithm
spellingShingle Mingchao Qi
JunQiang Zhao
Yan Feng
An optimized public opinion communication system in social media networks based on K-means cluster analysis
Heliyon
Cluster analysis
Social media
Network public opinion
Data mining
K-means algorithm
title An optimized public opinion communication system in social media networks based on K-means cluster analysis
title_full An optimized public opinion communication system in social media networks based on K-means cluster analysis
title_fullStr An optimized public opinion communication system in social media networks based on K-means cluster analysis
title_full_unstemmed An optimized public opinion communication system in social media networks based on K-means cluster analysis
title_short An optimized public opinion communication system in social media networks based on K-means cluster analysis
title_sort optimized public opinion communication system in social media networks based on k means cluster analysis
topic Cluster analysis
Social media
Network public opinion
Data mining
K-means algorithm
url http://www.sciencedirect.com/science/article/pii/S2405844024160641
work_keys_str_mv AT mingchaoqi anoptimizedpublicopinioncommunicationsysteminsocialmedianetworksbasedonkmeansclusteranalysis
AT junqiangzhao anoptimizedpublicopinioncommunicationsysteminsocialmedianetworksbasedonkmeansclusteranalysis
AT yanfeng anoptimizedpublicopinioncommunicationsysteminsocialmedianetworksbasedonkmeansclusteranalysis
AT mingchaoqi optimizedpublicopinioncommunicationsysteminsocialmedianetworksbasedonkmeansclusteranalysis
AT junqiangzhao optimizedpublicopinioncommunicationsysteminsocialmedianetworksbasedonkmeansclusteranalysis
AT yanfeng optimizedpublicopinioncommunicationsysteminsocialmedianetworksbasedonkmeansclusteranalysis