What the study found
Public opinion on Sina Weibo during Typhoon Muifa changed alongside the storm's activity, with discussion topics, attention, and sentiment all varying over time. The study found four main topic groups: typhoon impact, weather conditions, meteorological information, and disaster response.
Why the authors say this matters
The authors conclude that social media can serve as a real-time indicator of localized public sentiment during disasters. They also say that official risk narratives play a key role in shaping attention, and that the findings may help inform targeted risk communication and emergency management strategies.
What the researchers tested
The researchers analyzed 19,417 Sina Weibo microblog posts about Typhoon Muifa, which made four landfalls in China. They used LDA, or Latent Dirichlet Allocation, a topic-modeling method for grouping posts by theme, along with sentiment analysis and correlation statistics to examine how discussion evolved with the typhoon.
What worked and what didn't
Personal accounts mainly contributed to the typhoon impact and weather conditions topics, while official accounts dominated the meteorological information and disaster response topics. Daily total precipitation was strongly and positively correlated with the number of microblog posts (R² = 0.84, q < 0.001), especially in the forecasted landfall provinces Zhejiang, Shanghai, Shandong, and Liaoning (q < 0.05). Negative sentiment was also highly correlated with rising precipitation, largely through posts in the typhoon impact topic category.
What to keep in mind
The abstract does not describe detailed limitations. The summary is based only on Sina Weibo posts about one storm, Typhoon Muifa, so the findings are limited to that case as described.
Key points
- Four main discussion topics were identified: typhoon impact, weather conditions, meteorological information, and disaster response.
- Personal accounts mainly contributed to typhoon impact and weather conditions posts, while official accounts dominated meteorological information and disaster response.
- Daily precipitation had a strong positive correlation with the number of microblog posts (R² = 0.84, q < 0.001).
- Negative sentiment rose with increasing precipitation, largely through the typhoon impact topic.
- The authors say social media may act as a real-time indicator of localized public sentiment during disasters.
Disclosure
- Research title:
- Weibo opinion shifted with precipitation during Typhoon Muifa
- Authors:
- Yanran Sun, Qian Wang, Yongchang Zhu, Jing Xu, Lu Liu, Chunyi Xiang, Chuanhai Qian
- Institutions:
- Beijing Information Science & Technology University, China Meteorological Administration, Chinese Academy of Meteorological Sciences
- Publication date:
- 2026-02-23
- OpenAlex record:
- View
Get the weekly research newsletter
Stay current with peer-reviewed research without reading academic papers — one filtered digest, every Friday.