{"id":316,"date":"2016-11-09T17:46:41","date_gmt":"2016-11-09T17:46:41","guid":{"rendered":"https:\/\/copyright.lboro.ac.uk\/research\/?p=316"},"modified":"2017-08-14T12:03:42","modified_gmt":"2017-08-14T11:03:42","slug":"how-our-tool-analysing-emotions-on-twitter-predicted-donald-trump-win","status":"publish","type":"post","link":"https:\/\/blog.lboro.ac.uk\/research\/communication-culture-citizenship\/how-our-tool-analysing-emotions-on-twitter-predicted-donald-trump-win\/","title":{"rendered":"How our tool analysing emotions on Twitter predicted Donald Trump win"},"content":{"rendered":"

As the world dissects the how and why of Donald Trump\u2019s presidential victory<\/a>, pollsters are already coming under severe criticism for getting it so wrong<\/a>. But a tool we created that analysed emotions towards the two candidates on Twitter accurately predicted the result. 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.<\/p>\n

We first developed the tool, called EMOTIVE<\/a>, in 2013 to predict whether another riot could happen in London following those<\/a> in 2011. It can analyse thousands of tweets a second to extract from each tweet a direct expression of one of eight basic emotions: anger, disgust, fear, happiness, sadness, surprise, shame and confusion.<\/p>\n

We decided to use our tool to track emotions on Twitter around the world about the US presidential election for the three weeks leading up to the vote. During that period, our data showed that Trump continued to lead the race to the White House. Going by this tool, there were very few periods of time when Clinton was leading \u2013 contrary to what was being predicted by the polls.<\/p>\n

The EMOTIVE system worked by looking at how much fluctuation there was in the number of tweets relating specific emotions towards either Trump and Clinton. The more tweets with reference to an emotion fluctuate \u2013 reflecting greater uncertainty towards a candidate \u2013 the fewer votes the model predicts a candidate is going to get. Crucially, it\u2019s not the volume of tweets that matter, but the \u201cchoppiness\u201d that make the difference. This means that the model does not concern itself with the direction of the emotion or put value on one emotion over another \u2013 because an emotion such as anger can be positive or negative.<\/p>\n

\n

\"\"<\/a>

Emotions towards Trump. EMOTIVE, Author provided<\/p><\/div><\/figure>\n

This first graph shows how emotive tweets towards Trump fluctuated in that final 24-hour period. The y axis here measures what we call an emotional score. The wider the band of colour, the greater the number of emotive tweets related to that particular emotion, which means a greater outpouring of emotion towards Trump. But there was not a large amount of fluctuation overall in how much each emotion was appearing in tweets \u2013 meaning more voters were feeling more certain about their support for Trump.<\/p>\n

Now look at the second graph, showing the same data in relation to Hillary Clinton over a slightly longer period. This shows greater fluctuation \u2013 more spikes and dips \u2013 and meant she was predicted to win fewer votes.<\/p>\n

\n

\"\"<\/a>

Emotions towards Clinton. EMOTIVE, Author provided<\/p><\/div><\/figure>\n

A good gauge of the public mood<\/h2>\n

When we analysed the raw tweets we saw an unprecedented campaign with a race all about personalities, dominated by attacks on Trump and Clinton.<\/p>\n

\n

People who are more scared of #Trump<\/a> than #Hillary<\/a> are either
1. Stupid 2. Ignorant 3. Corrupt 4. Illegal<\/p>\n

— Spangladesh (@sspangler15) November 8, 2016<\/a><\/p><\/blockquote>\n