Home » Courses » Loughborough system predicted Trump's win

Loughborough system predicted Trump's win

28th November 2017 Posted by: Duncan Chisholm - Editor

RELYING on Western media since Trump announced his Republican candidacy has perhaps felt like a media version of a never-ending thunderstorm, with a grim horizon and a daily flash of lightning in the headlines. Weary foreboding over what limit of taste Trump will gleefully break next has taken the place of the shock felt by Westerners since election night on November 8.

Let’s remember that, in the days which followed, panic ensued – David Brooks of the New York Times, almost a year on from the Trump win, has compared the election result to the Russian Revolution: "This is like 1917, a clash of political, moral, economic and social ideologies all rolled into one."

David Frum, of the prestigious Atlantic magazine, started sketching out details about how Trump could achieve an American autocracy, and a prominent UK political commentator assured readers of The Spectator that Trump would be a much, much worse incumbent than he had been a candidate.

In the days before the vote, America’s most authoritative institutions such as the New York Times estimated Clinton had a very high chance of winning the race. But following Trump’s win, US political polls were branded “broken.”

Yet one organisation had been consistent in their prediction that Trump would get over the line and was proved right – the Centre for Information Management, led by Professor Tom Jackson at Loughborough University.

They explain the fundamentals of their approach as having an advantage over polls which capture a moment in time: “Unlike other poll predictors that just take a snapshot in time, our tool used real-time data from Twitter which provides a more accurate picture of who people are likely to vote for.”

The Centre for Information Management’s EMOTIVE programme is capable of analysing thousands of tweets a second to scan for direct expressions of one of eight basic emotions: anger, disgust, fear, happiness, sadness, surprise, shame and confusion. 

The EMOTIVE system scanned the fluctuation in the emotion of tweets in relation to Trump and Clinton, so volume was not taken into consideration: "The more tweets with reference to an emotion fluctuate – reflecting greater uncertainty towards a candidate – the fewer votes the model predicts a candidate is going to get." The visual illustrations of the EMOTIVE system's finding are available here

Perhaps ominously for those who would rather that political debate included actual policies, the EMOTIVE team observed that much of the material they analysed contained little mention of policies and how the candidates' proposals might actually affect the world in the US and beyond. 

The system was set up following the 2011 England Riots, after it became clear that social media had played a major role in the communications of rioters, and the system was used to successfully predict the outcome of the 2015 General Election. 

Loughborough University, where the Centre for Information Management is based, is now ranked in among the Top 10 in all of the authoritative UK university rankings lists which are compiled by The Times, The Guardian and the Complete University Guide. 


This editorial was sponsored by Loughborough University, to find out more about their courses take a look at their profile.







Sign up for our newsletter

Follow Us

© 2018 Student World Online Registered in England and Wales 08074528
Terms of Use | Privacy Policy | Contact us