6 million social media conversations got it just right

The bookies got it wrong, the telephone polls were inaccurate, the punters were off. But at 4.30 pm yesterday, the SENSEI project, using Websays technology, predicted the Brexit referendum outcome almost exactly.

Earlier in the day, the polling booths opened across the UK, social media chatter was 49.63% in favour of leave and 50.37 in favour of staying in the EU with no undecideds in the social media mix and it was too close to call.

But by late afternoon, social media chatter had changed as more and more undecided voters took their decision and there was a dramatic swing to Leave. 48% Remain, 52% Leave. And that’s exactly how it ended up.


Brexit Prediction

Most of the traditional polls were predicting a Remain victory. The bookies were confident it was going to be a Remain victory. The media pundits were mostly predicting a Remain victory. Even Nigel Farage had almost conceded defeat. But social media got it right.

According to Prof. Giuseppe Riccardi of the University of Trento and SENSEI’s Project Co-ordinator: “Over the course of this campaign, the SENSEI project’s unique combination of humans and machine reading algorithms has listened to more than 6 million social media conversations relating to the Brexit vote to identify and predict voting sentiment.

We are delighted that, following our equally accurate prediction of the Spanish general election last year, we have once again predicted the outcome of a major political event with very high accuracy. It appears that the momentum on UK social media started to change on June 21st and we watched it move”.

The SENSEI project, in conjunction with web crawling and text analytics experts Websays, has been applying a unique combination of advanced technology and human intervention over the course of the referendum to see if their combination of “man and machine” can more accurately predict the outcome of the referendum than traditional pollsters.

Dr. Hugo Zaragoza, founder of Websays and a worldwide expert in opinion analytics, said: “Once again, our data told a very different story to the pollsters and we were proved to be more accurate. This is a great result for the project. The ability to listen to millions of pieces of conversations and then analysing them for sentiment, using a combination of humans and machines, has proved once again to be more successful than traditional polling methods.

“This is a really powerful tool for politics and business and after the second disastrous set of predictions from the main players, we have demonstrated how accurate our technique is. At times, the social media chatter was intense and passionate Since we started this project, we have listened to and analysed 300,000 social media conversations on Brexit every day and we’re delighted to have called the result correctly.”

The SENSEI project is a pan-European, public-private partnership set up to make sense of the millions of blog posts and social media conversations that occur every day and it has the ultimate goal of adding real commercial value to this research. Websays and SIS Lab (University of Trento), the creators of Sensei are leading industry and research groups within the SENSEI consortium, which includes the University of Essex, Aix Marseille and Sheffield as partners.

The SENSEI project demonstrates how a powerful combination of technology-driven search engines, combined with a unique qualitative approach using human intervention, can fundamentally change the way we understand social media chatter and how it can be applied commercially to help commentators to understand what is being said.



The SENSEI project is funded by the FP7 programme of the European Commission (2013-2016). The SENSEI project aims to create technology and services to analyse human conversations from diverse media sources (e.g. speech, social media etc.). Academic and business partners at SENSEI are extracting value from human conversations and supporting end-users, analysts and decision makers in dealing with massive conversation streams. For more information and details visit the consortium website at http://www.sensei-conversation.eu.