Social media can be used for a number of interesting things as ways to aggregate accurate social data become more accurate.
Scientists from George Washington University and John Hopkins University claim their approach, which uses Twitter, is proven to be very accurate at the task.
This isn’t the first time social media has been used in an attempt to track the flu. The Google Flu tracker was recently heavily criticized, when cases returned data that pointed towards the tracker being overestimated due to flaws in ‘big data’.
In the flu season during 2012 and 2013, the new Twitter flu tracker was 93% accurate when in comparison with the actual national flu data which is collected by the Centers for Disease Control and Prevention.
The tracker was also applied to New York City and the results came back to be 88% accurate.
The weekly change in which flu cases would increase or decrease was also predicted with 85% accuracy according to a study published in the PLOS One Journal.
The Center for Disease Control and Prevention’s data is collected from physicians and hospitals which means there is a significant delay in reports. Using Twitter could reveal spikes in flu cases much quicker.
0 Comments