What if we can predict social movements, consumer reactions or even possible outbreaks of epidemics up to two months in advance just by monitoring 50,000 Twitter accounts?
Researchers have found a simple and effective method for monitoring social networks where data from just 50,000 Twitter accounts is enough to achieve these levels of prediction and to know what will “go viral” across the entire internet. Scientists from Universidad Carlos III of Madrid (UC3M) and Universidad Autanoma of Madrid were among those who did the research. The aim was to test what is known as the “sensors hypothesis” on the social networks.
The research team randomly selected a group of users and took some of their followers as the sensor group.
It found that those ‘sensor-friends’ play a more important role than what was previously believed, because they receive information long before the previously chosen users.
For example, the sensor model predicted the viral rise of the hashtag ‘#Obamacare’ as a Twitter trend.