Insight into public sentiment and demand in China’s public health emergency response: a weibo data analysis
Abstract Background During the COVID-19 pandemic, public sentiment and demands have been prominently reflected on social media platforms like Weibo. Understanding these sentiments and demands is crucial for governments, health officials, and policymakers to make effective responses and adjustments....
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-04-01
|
| Series: | BMC Public Health |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12889-025-22553-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849726195758792704 |
|---|---|
| author | Yanping Wang Min Wei Peng Wang Yiran Gao Tian Yu Nan Meng Huan Liu Xin Zhang Kexin Wang Qunhong Wu |
| author_facet | Yanping Wang Min Wei Peng Wang Yiran Gao Tian Yu Nan Meng Huan Liu Xin Zhang Kexin Wang Qunhong Wu |
| author_sort | Yanping Wang |
| collection | DOAJ |
| description | Abstract Background During the COVID-19 pandemic, public sentiment and demands have been prominently reflected on social media platforms like Weibo. Understanding these sentiments and demands is crucial for governments, health officials, and policymakers to make effective responses and adjustments. Objective The study aims to analyze public sentiment and identify key demands concerning COVID-19 policies and social issues using Weibo data, providing insights to improve China’s policies and legal systems in public health emergencies. Methods The study used Python tools to collect public opinion data from Weibo regarding policy adjustments, social issues, and livelihood concerns. A total of 50,249 valid comments on 100 blog posts were collected from December 2019 to October 2023 in China. The SnowNLP algorithm was employed for sentiment analysis, Latent Dirichlet Allocation was used for topic clustering, and sampling coding was applied to further explore public demands by condensing the comment texts. Results The study categorized 100 blog posts into 23 important topics, with average sentiment scores ranging from 0.24 to 0.66. These scores ranging from 0 to 1 reflect sentiment polarity, where lower values indicate more negative public sentiment. The topics of material safety and information security management had the lowest scores, at 0.24 and 0.34, respectively. The analysis further revealed that the 23 topics could be classified into 57 subtopics, and a total of 101 concepts were identified through coding. The study found that public demands fall into five key categories: transportation and travel security, epidemic protection and health security, law building and policy implementation, social services and public demand, and education demand. Conclusions The study underscores the complexity of public sentiment during the epidemic, with significant concerns about material safety and information security management. Public demands span basic survival needs to higher-order concerns such as education and legal protections. The findings suggest that policy-making processes must become more responsive, transparent, and equitable, incorporating real-time public feedback and ensuring comprehensive policies and legal systems are in place to address multifaceted public demands effectively. |
| format | Article |
| id | doaj-art-40ba07af3bdd4625af6441aff5efa70e |
| institution | DOAJ |
| issn | 1471-2458 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Public Health |
| spelling | doaj-art-40ba07af3bdd4625af6441aff5efa70e2025-08-20T03:10:16ZengBMCBMC Public Health1471-24582025-04-0125111310.1186/s12889-025-22553-2Insight into public sentiment and demand in China’s public health emergency response: a weibo data analysisYanping Wang0Min Wei1Peng Wang2Yiran Gao3Tian Yu4Nan Meng5Huan Liu6Xin Zhang7Kexin Wang8Qunhong Wu9School of Health Management, Harbin Medical UniversitySchool of Health Management, Harbin Medical UniversitySchool of Health Management, Harbin Medical UniversitySchool of Health Management, Harbin Medical UniversitySchool of Health Management, Harbin Medical UniversitySchool of Health Management, Harbin Medical UniversitySchool of Health Management, Harbin Medical UniversitySchool of Health Management, Harbin Medical UniversitySchool of Health Management, Harbin Medical UniversitySchool of Health Management, Harbin Medical UniversityAbstract Background During the COVID-19 pandemic, public sentiment and demands have been prominently reflected on social media platforms like Weibo. Understanding these sentiments and demands is crucial for governments, health officials, and policymakers to make effective responses and adjustments. Objective The study aims to analyze public sentiment and identify key demands concerning COVID-19 policies and social issues using Weibo data, providing insights to improve China’s policies and legal systems in public health emergencies. Methods The study used Python tools to collect public opinion data from Weibo regarding policy adjustments, social issues, and livelihood concerns. A total of 50,249 valid comments on 100 blog posts were collected from December 2019 to October 2023 in China. The SnowNLP algorithm was employed for sentiment analysis, Latent Dirichlet Allocation was used for topic clustering, and sampling coding was applied to further explore public demands by condensing the comment texts. Results The study categorized 100 blog posts into 23 important topics, with average sentiment scores ranging from 0.24 to 0.66. These scores ranging from 0 to 1 reflect sentiment polarity, where lower values indicate more negative public sentiment. The topics of material safety and information security management had the lowest scores, at 0.24 and 0.34, respectively. The analysis further revealed that the 23 topics could be classified into 57 subtopics, and a total of 101 concepts were identified through coding. The study found that public demands fall into five key categories: transportation and travel security, epidemic protection and health security, law building and policy implementation, social services and public demand, and education demand. Conclusions The study underscores the complexity of public sentiment during the epidemic, with significant concerns about material safety and information security management. Public demands span basic survival needs to higher-order concerns such as education and legal protections. The findings suggest that policy-making processes must become more responsive, transparent, and equitable, incorporating real-time public feedback and ensuring comprehensive policies and legal systems are in place to address multifaceted public demands effectively.https://doi.org/10.1186/s12889-025-22553-2COVID-19Public opinionLatent dirichlet allocationSentiment analysisPublic health emergency |
| spellingShingle | Yanping Wang Min Wei Peng Wang Yiran Gao Tian Yu Nan Meng Huan Liu Xin Zhang Kexin Wang Qunhong Wu Insight into public sentiment and demand in China’s public health emergency response: a weibo data analysis BMC Public Health COVID-19 Public opinion Latent dirichlet allocation Sentiment analysis Public health emergency |
| title | Insight into public sentiment and demand in China’s public health emergency response: a weibo data analysis |
| title_full | Insight into public sentiment and demand in China’s public health emergency response: a weibo data analysis |
| title_fullStr | Insight into public sentiment and demand in China’s public health emergency response: a weibo data analysis |
| title_full_unstemmed | Insight into public sentiment and demand in China’s public health emergency response: a weibo data analysis |
| title_short | Insight into public sentiment and demand in China’s public health emergency response: a weibo data analysis |
| title_sort | insight into public sentiment and demand in china s public health emergency response a weibo data analysis |
| topic | COVID-19 Public opinion Latent dirichlet allocation Sentiment analysis Public health emergency |
| url | https://doi.org/10.1186/s12889-025-22553-2 |
| work_keys_str_mv | AT yanpingwang insightintopublicsentimentanddemandinchinaspublichealthemergencyresponseaweibodataanalysis AT minwei insightintopublicsentimentanddemandinchinaspublichealthemergencyresponseaweibodataanalysis AT pengwang insightintopublicsentimentanddemandinchinaspublichealthemergencyresponseaweibodataanalysis AT yirangao insightintopublicsentimentanddemandinchinaspublichealthemergencyresponseaweibodataanalysis AT tianyu insightintopublicsentimentanddemandinchinaspublichealthemergencyresponseaweibodataanalysis AT nanmeng insightintopublicsentimentanddemandinchinaspublichealthemergencyresponseaweibodataanalysis AT huanliu insightintopublicsentimentanddemandinchinaspublichealthemergencyresponseaweibodataanalysis AT xinzhang insightintopublicsentimentanddemandinchinaspublichealthemergencyresponseaweibodataanalysis AT kexinwang insightintopublicsentimentanddemandinchinaspublichealthemergencyresponseaweibodataanalysis AT qunhongwu insightintopublicsentimentanddemandinchinaspublichealthemergencyresponseaweibodataanalysis |