School of Business and Economics

News



4 Nov 2016

SBE academics use EMOTIVE computer program to predict outcome of the US presidential campaign

Professor Tom Jackson and Dr Martin Sykora

School of Business and Economics academics are capturing people’s feelings towards the US presidential election on social media using their unique EMOTIVE computer program that can analyse up to 3,000 tweets a second.

Using intricate software, the EMOTIVE system pulls from each tweet a direct expression of one of 8 basic emotions: happiness, anger, disgust, fear, surprise, shame, sadness and confusion. In the past this system has been used to monitor reactions of the public to major events, for example the recent Paris terrorist attacks. Additionally, last year the EMOTIVE system correctly predicted the outcome of the UK General Election.

The research team behind this program, from the School of Business and Economics, are hoping to use EMOTIVE to predict who will be taking up office in this year’s US Presidential campaign.  

Professor Tom Jackson, Associate Dean [Research] at the SBE and head of the EMOTIVE team, said this in regards to the research:

Twitter is a very concise platform through which users express publicly how they feel about a particular event, be that a criminal act, an election or even a change in the weather.

We have already shown what a fantastic tool EMOTIVE is in capturing through Twitter the public’s mood. The system gives us, in real time, a snapshot of how people are really feeling and from this, when looking at an election, we can make a prediction of how these feelings will be reflected in voting.

It also enables to see how people’s emotions towards each candidate change, minute by minute. From our data so far it is a very close fought campaign, which the traditional polls have not shown!

Dr Martin Sykora, a Lecturer in Information Management and is also a part of the EMOTIVE team, added:

The system we created takes the eight emotions and gives them a rich linguistic context so that we can chart the strength of emotions expressed in ordinary language and also in slang.  We can view how reactions grow and diminish over time towards Trump and Clinton.

There is a dedicated EMOTIVE website for the US elections, where you can track in real time the public’s feelings to the presidential race and which candidate is currently in the lead. The system is tracking and analysing tweets with the following hashtags: #Tump, #Trump2016, #Hillary, Hillary2016, #MakeAmericaGreatAgain, #ImWithHer. In the last 24 hours it has looked at more than 40,000 tweets.