We have been working on pandemics and contagion phenomena long enough to deserve a little fun on a more frivolous but compelling case study for the debate about the predictive power of big data analytics. In the new paper posted in the arxiv "Beating the news using social Media: the case study of American Idol" we focus on the elimination of contestants in the American Idol TV shows as an example of a well defined voting phenomenon that each week draws millions of votes in the USA. We provide evidence that Twitter activity during the time span defined by the TV show airing and the voting period following it, correlates with the contestants ranking and allows the anticipation of the voting outcome. Furthermore, the fraction of Tweets that contain geolocation information allows us to map the fanbase of each contestant, both within the US and abroad, showing that strong regional polarizations occur.
We did not make any predictions about the final outcome of the show, yet. In order to infer the Top voted contestant we need the data that will become available on Tuesday May 22 night EST time and we will upload a revised manuscript before the the season finale.
We did not make any predictions about the final outcome of the show, yet. In order to infer the Top voted contestant we need the data that will become available on Tuesday May 22 night EST time and we will upload a revised manuscript before the the season finale.
RSS Feed