Covid-19 ravaged the world and caused panic among mankind. In the age of social networks, viruses are still spreading through contact, but fear spreads across the Internet, forming a social infectious disease that is more infectious than viruses.
After the outbreak of Covid-19,, through big data analysis of rumors, fear, and bullying on Taiwan’s social media, we calculated the 15 most harmful things.
Compared with the R0 of virus infection, the R0 of fear infection on social media is 40 times higher. A post with fear component spread out, which will cause 11.9 posts or messages with fear.
1. Strengthen the public’s awareness and verification of fake news.
2. Through quantitative analysis, readers understand the breadth and intensity of fear on social media during the epidemic.
3. The public has more understanding and empathy for quarantined and infected people.
4. The government protects the privacy of those diagnosed in the follow-up investigation, and begins to promote the people to have a positive attitude towards the quarantined.
1.Observe tens of thousands of website channels through the KEYPO system, including major news channels, social media, discussion boards, and blogs, and analyze Covid-19 related texts.
2. Refer to Motional Contagion of risk perception author David Ropeik, and divide the speeches of Taiwanese on social media into three fear categories.
3. According to the epidemiologist Adam Kucharski’s epidemiological R0 model parameters, the R0 of fear spread in the Taiwan community is calculated to be 11.9.
What was the hardest part of this project?
We conduct text analysis by observing tens of thousands of websites and channels in Taiwan, including major news channels, social platforms, discussion boards and blogs.
We display the fear distribution map, the fear transmission path map, the keywords of attitude and behavior, and the R0 of fear infection on social media, and present its changes with dynamic charts and short videos.
Refer to the related theories of risk perception author and epidemiology, and transform the data into legibility results, making it easier for readers to understand the infodemic on the social media and the phenomenon of fears spreading caused by it.
What can others learn from this project?
Through data analysis, we can understand the changes in public opinion more widely, and classify and redefine fears in social media. Increase the credibility and richness of reports.