NEW YORK — Scientists have devised a means to predict the outcome of election-based processes such as TV talent shows through the big data analysis of tweets

Fabio Ciulla from Northeastern University, Boston, USA, and his colleagues demonstrated that the elimination of contestants in TV talent shows based on public voting, such as American Idol, can be anticipated. They unveiled the predictive power of microblogging Twitter signals-used as a proxy for the general preference of an audience-in a study recently published in EPJ Data Science¹.
The authors considered the voting system of these shows as a basic test to assess the predictive power of Twitter signals. They relied on the overlap between Twitter users and show audience to collect extremely detailed data on social behaviour on a massive scale. This approach provided a unique and unprecedented opportunity to apply network science to social media. Social phenomena can thus be studied in a completely unobtrusive way. Previously, Twitter has already been used to forecast epidemics spreading, stock market behaviour and election outcomes with varying degrees of success.

In this study, the authors demonstrated that the Twitter activity during the time span limited to the TV show airing and the voting period following it […]