Using Twitter to Track Disease Activity During the H1N1 Pandemic
Author Information
Author(s): Alessio Signorini, Alberto Maria Segre, Philip M. Polgreen
Primary Institution: University of Iowa
Hypothesis
Can Twitter data be used to track public sentiment and actual disease activity during the H1N1 pandemic?
Conclusion
Twitter data can accurately track reported disease levels and public concern regarding H1N1.
Supporting Evidence
- Twitter data can provide real-time estimates of disease activity.
- Public interest in H1N1-related topics fluctuated with reported disease levels.
- Estimates of influenza-like illness derived from Twitter chatter closely matched reported disease levels.
Takeaway
The study shows that tweets about the flu can help us understand how many people are sick and how worried people are about it.
Methodology
The study collected and analyzed tweets containing specific keywords related to H1N1 to estimate disease activity and public sentiment.
Potential Biases
The analysis may be biased due to the non-representative nature of Twitter users and the exclusion of non-English tweets.
Limitations
The study is limited by the demographic representation of Twitter users and the variability in tweet volume across different times and regions.
Participant Demographics
Demographics of Twitter users are not well-defined and may not represent the general population.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website