Accès libre

A Clustering Study of Online Public Opinion Texts on Public Emergency Events Based on Sentence-Level Similarity and Sentiment Analysis

Yaxian Qiu

Yaxian Qiu

Shanxi Police CollegeTaiyuan, China
Recherchez cet auteur sur
Sciendo|Google Scholar
Qiu, Yaxian
 et 
Hui Han

Hui Han

Shanxi Police CollegeTaiyuan, China
Recherchez cet auteur sur
Sciendo|Google Scholar
Han, Hui
  
25 sept. 2025
A Clustering Study of Online Public Opinion Texts on Public Emergency Events Based on Sentence-Level Similarity and Sentiment Analysis's Cover Image
À propos de cet article
Article précédent
Article suivant
Citez
Télécharger la couverture
Publié en ligne: 25 sept. 2025
Reçu: 31 janv. 2025
Accepté: 10 mai 2025
DOI: https://doi.org/10.2478/amns-2025-1018
Mots clés
© 2025 Yaxian Qiu and Hui Han, published by Sciendo
This work is licensed under the Creative Commons Attribution 4.0 International License.

Figure 1.

Network public opinion analysis system model for public emergencies
Network public opinion analysis system model for public emergencies

Figure 2.

Two-state Kleinberg state machine model
Two-state Kleinberg state machine model

Figure 3.

Infinite state Kleinberg state machine model
Infinite state Kleinberg state machine model

Figure 4.

Public opinion heat distribution and trend
Public opinion heat distribution and trend

Figure 5.

Top 10 positive emotion words
Top 10 positive emotion words

Figure 6.

Top 10 negative emotion words
Top 10 negative emotion words

Figure 7.

Timing of Weibo emotion intensity
Timing of Weibo emotion intensity

Figure 8.

F-measure comparison diagram
F-measure comparison diagram

Figure 9.

Purity comparison diagram
Purity comparison diagram

Figure 10.

Weibo comments hot topic evolution
Weibo comments hot topic evolution

Online public opinion heat value (part)

Date Original tweets Forwarding Comment Oi Oi’
0720 812 25 1628 411.8 0.06029
0721 3729 64 4729 734.3 0.16725
0722 10283 2547 6248 8403.6 0.96792
0723 12272 1164 6027 8684.4 1
0724 8281 75 3143 3989.1 0.65322
0725 7934 42 1983 2933.6 0.54855
0726 4032 50 732 512.9 0.20316
0727 2224 44 461 83.8 0.12149
0728 1034 32 223 33.1 0.12883
0729 623 10 56 21.4 0.03946
0730 324 7 30 17.5 0.02181
0731 182 5 12 16.7 0.01486
0801 148 3 4 13.3 0.00740
0802 137 0 2 0 0.00083
0803 84 0 1 0 0.00034

Example of results of topic term frequency

Initial period Eruption period Recurrent period Flat period
Keyword Time Keyword Time Keyword Time Keyword Time
Rainstorm 273 Be trapped 583 Volunteer 146 Flood prevention 37
Forewarning 231 Tunnel 422 Donation 93 Rectify and reform 30
Zhengzhou 219 Message 394 Reestablish 90 Commemorate 26
Weather 210 Ask for help 361 Accountability 74 Sponge city 20
Subway 187 Fighting 347 Investigation 69 Policy 19
Hydrops 162 Casualties 328 Insurance 66 Present a bouquet 15
Off-line 98 rescue 287 Recover 57 R.I.P 14
Notification 67 Line 5 253 Drain water 48 Recover 10
Traffic 52 Fireman 218 Settle 39
Weather bureau 21 Submerge 184 victim 31
Langue:
Anglais
Périodicité:
1 fois par an
Sujets de la revue:
Sciences de la vie, Sciences de la vie, autres, Mathématiques, Mathématiques appliquées, Mathématiques générales, Physique, Physique, autres
RSS Feed de la revue