Li, J., Xu, Q., Cuomo, R., Purushothaman, V., & Mackey, T. (2020). Data mining and content analysis of the Chinese social media platform Weibo during the early COVID-19 outbreak: retrospective observational infoveillance study. JMIR public health and surveillance, 6(2), e18700. https://publichealth.jmir.org/2020/2/e18700/

University of Michigan - Ann Arbor

- Researchers conducted both quantitative and qualitative analyses of Weibo posts about Covid-19 to see if they’re indicative or even predictive of the number of cases reported and study the most commonly discussed Covid-19-related topics on Weibo 
- Sina Weibo is the Chinese equivalent of Twitter and is largely used to share all sorts of content
- Weibo users’ discussions and perceptions altered with the release of new information
- There is a positive correlation between Weibo posts about Covid-19 and the number of cases officially reported in Wuhan at the beginning of the pandemic, meaning that Weibo posts can be used as a measure of changes in case counts 

Data mining and content analysis of the Chinese social media platform Weibo during the early COVID-19 outbreak: retrospective observational infoveillance study

Observational infoveillance study
- Used Python to collect Covid-19-related Weibo posts from December 23, 2019 to January 30, 2020 containing certain keywords
- Categorized posts by geographic location and separated posts from Wuhan to focus on 
- Chinese National Health Commission data for official case counts 
- Collected a total of 115,299 posts; average of 2,956 posts per day

Quantitative analysis
- Categorized posts by calendar day
- Visualized longitudinal trends and ran simple regression models for posts per day and daily cases reported 
- Interested in seeing whether simple regression models could accurately predict changes in daily case counts using the number of daily Weibo posts 

Qualitative analysis 
- To observe trends and common themes mentioned among users  
- Binary coding approach to label posts as containing relevant Covid-19 information and news or irrelevant information
- Thematic content analysis used to determine frequently mentioned topics
- Chose most common topics as parent classifications and proceeded to categorize posts into these identifications 

Data mining and content analysis of the Chinese social media platform Weibo during the early COVID-19 outbreak: retrospective observational infoveillance study methodology

Data mining and content analysis of the Chinese social media platform Weibo during the early COVID-19 outbreak: retrospective observational infoveillance study 

Learn Before

Related