Twitter data crunching: The new crystal ball

August 29, 2012

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 correlated with the contestants' ranking. As a result, it helped predict the outcome of the votes. This approach offers a simplified version helping to analyse complex societal phenomena such as political elections. Unlike previous voting systems, Twitter offers a quantitative indicator that can act as proxy for what is occurring around the world in real time, thereby anticipating the outcome of future events based on opinions.

Ciulla and colleagues also showed that the fraction of tweets that included geolocalisation information enabled to internationally map the fan base of each contestant. They identified a strong influence by the geographical origin of the votes, suggesting a different outcome to the show, if voting had not been limited to US voters.
-end-
Reference

1. F. Ciulla, D. Mocanu, A. Baronchelli, B. Goncalves, N. Perra, A. Vespignani (2012). Beating the news using Social Media: the case study of American Idol. European Physical Journal Data Science; DOI 10.1140/epjds8

For more information, please visit www.epj.org

The full-text article is available to journalists on request.

Springer

Related Twitter Articles from Brightsurf:

How Twitter takes votes away from Trump but not from Republicans
In the 2016 US presidential election, Twitter made independent voters less likely to vote for Donald Trump, finds new study from Bocconi University and Princeton

Study tracks public concerns on Twitter about COVID-19
Twitter users initially didn't feel positive about the state of the economy, prevention, treatment and recovery concerning COVID-19.

How a Twitter hashtag provides support for people with breast cancer
A UCLA-led review of nine years of social media posts with the hashtag #BCSM suggests that Twitter can be a useful resource not only for patients, but also for physicians and researchers.

QUT algorithm could quash Twitter abuse of women
Online abuse targeting women, including threats of harm or sexual violence, has proliferated across all social media platforms but QUT researchers have developed a sophisticated statistical model to identify misogynistic content and help drum it out of the Twittersphere.

A novel strategy for quickly identifying twitter trolls
Two algorithms that account for distinctive use of repeated words and word pairs require as few as 50 tweets to accurately distinguish deceptive ''troll'' messages from those posted by public figures.

Journalists' Twitter use shows them talking within smaller bubbles
Journalists in Washington, D.C., have long been accused of living in a ''Beltway bubble.'' Their interactions on Twitter, however, show them congregating in even smaller ''microbubbles,'' says a recent study.

Twitter data reveals global communication network
Twitter mentions show distinct community structure patterns resulting from communication preferences of individuals affected by physical distance between users and commonalities, such as shared language and history.

Twitter data research reveals more about what patients think about statins
More than one in seven people taking statins -- prescribed to lower cholesterol levels -- believed that meant they could still eat unhealthy foods, a new study shows.

Twitter posts reveal polarization in Congress on COVID-19
The rapid politicization of the COVID-19 pandemic can be seen in messages members of the US Congress sent about the issue on the social media site Twitter, a new analysis found.

Candidates who use humor on Twitter may find the joke is on them
Political candidates' use of humor on social media could sometimes backfire on them with potential supporters, new research suggests.

Read More: Twitter News and Twitter Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.