2021
DOI: 10.1016/j.dsm.2021.07.001
|View full text |Cite
|
Sign up to set email alerts
|

Improving Google Flu Trends for COVID-19 estimates using Weibo posts

Abstract: While incomplete non-medical data has been integrated into prediction models for epidemics, the accuracy and the generalizability of the data are difficult to guarantee. To comprehensively evaluate the ability and applicability of using social media data to predict the development of COVID-19, a new confirmed case prediction algorithm improving the Google Flu Trends algorithm is established, called Weibo COVID-19 Trends (WCT), based on the post dataset generated by all users in Wuhan on Sina Weibo. A genetic a… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
8
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
7
1

Relationship

2
6

Authors

Journals

citations
Cited by 15 publications
(8 citation statements)
references
References 47 publications
0
8
0
Order By: Relevance
“…In research related to the COVID-19 vaccine, using social media data for academic research has become an emerging trend. Social media provides a rich volume of real-time and cost-effective content including news, events, public comments, etc., [ 5 ], which has been widely used in health-related issues and public health crises [ 6 , 7 , 8 , 9 ]. However, research on the COVID-19 vaccine mainly employs the classic time series analysis based on discrete observation data.…”
Section: Introductionmentioning
confidence: 99%
“…In research related to the COVID-19 vaccine, using social media data for academic research has become an emerging trend. Social media provides a rich volume of real-time and cost-effective content including news, events, public comments, etc., [ 5 ], which has been widely used in health-related issues and public health crises [ 6 , 7 , 8 , 9 ]. However, research on the COVID-19 vaccine mainly employs the classic time series analysis based on discrete observation data.…”
Section: Introductionmentioning
confidence: 99%
“…Next, we calculated the number of microblogs containing keywords from the three categories. From Figure 1 , we can see that Basic awareness is the type with the largest number of microblogs related to the epidemic, which indicates most people's concern primarily focus on Basic awareness rather than some awareness deeper like “mask” and “social distance.” Also, the changes in the number of various microblogs have a similar trend with the increase of confirmed cases and a particular role in early warning ( 41 , 42 ).…”
Section: Resultsmentioning
confidence: 78%
“…The unprecedented magnitude and transmission speed of COVID-19 has intensified massive social media activities as people are isolated at home to break infection chains [ 21 26 ]. The large amount of social data generated by online users can help us understand the topics of concern and emotional fluctuations of the epidemic-related population in real time, which is necessary for timely detection of people’s needs and emotional counselling.…”
Section: Related Workmentioning
confidence: 99%