Twitter reveals that the UK will vote to leave the EU

Map showing Twitter and EU referendum voting intentionsThe majority of people Tweeting about the forthcoming referendum on the UK’s membership of the EU are going to vote “leave”. That’s the surprising finding in a study of more than 350,000 Tweets on the topic.

Of course, you could easily dismiss this research as being superficial and without any controls. Equally, you could say that the “Brexiters” are more likely to Tweet than those who want to remain within the EU.

But you could be wrong.

Twitter sentiment analysis is amazingly accurate. For instance, it is more capable of predicting heart attack mortality than existing medical technologies. Equally, Twitter appears to be more capable of predicting stock market prices than other methods. Twitter can also accurately predict the extent of hurricane damage. Clearly, Twitter is not bad at predictions.

So, the prediction that most people will vote “leave” should not be taken lightly. This new analysis of sentiment on the referendum could be a significant finding.

If you look at the map, the blue areas show where sentiment is highest to remain. Wales, for instance, which has received significant funding from the EU is almost entirely in favour of remaining. Areas heavily affected by immigration, such as Kent and East Anglia (red on the map) are set against the EU and are Tweeting to leave. According to the research, the town in the UK with the highest number of Tweets about remaining in the EU is Reading, Berkshire. Interestingly, this town has the European HQs of many significant global businesses, including Microsoft. Could that be a reason for the number of Tweets in favour – several people who work in that town are often travelling throughout Europe anyway?

With more than 2,500 Tweets per second, Twitter is a real barometer of opinion. Unlike market research or polls, for example, which can only ask a tiny proportion of people at any one time, Twitter can give you the feelings of hundreds of thousands – even millions – of people and see their opinions alter over time. Currently, pollsters telephone only around 1,000 people. They can tell us the statistical significance, but Twitter can give us a much more complete picture of feelings from bigger samples of people.

True, the Twitter sample is self-selected, made of people who want to have their say, rather than the general population which tends to remain quiet. However, even though Twitter may be biased, it is probably representative because people’s opinions are constructed from the world in which they inhabit. So someone who Tweets is representing the people around them and their thoughts too.

If you are in business, you cannot ignore Twitter as a research tool. It can predict the likely popularity of products and services, for instance, as well as show you what your customers really want.

So, while you set up your own Twitter sentiment study, sit back and remember that you heard it here first: the UK is going to vote to leave the EU (according to Twitter).

17279

Get blog posts like this each week

Sign up to receive my weekly blog digest every Monday

Graham Jones
Graham Jones is an Internet Psychologist who studies the way people use the online world, in particular how people engage with businesses. He uses this knowledge to help companies improve their online connections to their customers and potential customers and offers consultancy, workshops, masterclasses and webinars. He also speaks regularly at conferences and business events. Graham is an award-winning writer and the author of 32 books, several of which are about various aspects of the Internet. For more information connect with me on Google+
Graham Jones

@grahamjones

Graham Jones is an Internet Psychologist, professional speaker and author of 32 books who helps businesses understand the online behaviour of their customers
My week on Twitter 🎉: 13 Mentions, 130K Mention Reach, 10 Likes, 5 Retweets, 38.1K Retweet Reach. See yours with… https://t.co/64wRqKBqQb - 2 hours ago
Graham Jones

23 thoughts on “Twitter reveals that the UK will vote to leave the EU

  1. Someone mentioned that the bookies have an outvote at 4-1 and I thought, are they trying to influence the masses into a yes… Think I’ll go stick 100 quid on it tomorrow! And I forecast seeing you on TV news before the week is out talking Brexit … That’s my boy 😉

    • The odds in favour of a remain vote have been reducing for weeks now. There is still three weeks to go, so they could go the other way and favour a leave vote. Bookies rarely get it wrong. The financial markets are also showing concern about the likelihood of a leave vote. When you have the bookies getting twitchy as well as the financial markets and Twitter data showing the same thing, it suggests another possibility – that this referendum will not be decisive one way or the other.

      • If the bookies rarely get it wrong why are they odds on staying in that’s totally contradictory to what you are saying here with your TWIT research come on !!!

        • I don’t agree that it is “totally” contradictory. For most of the bookies (I agree not all) the odds have been changing over the past few months, with them making Brexit more likely than was the case a months or two back. The graph of odds for many bookies (not all) shows the betting for “leave” and the betting for “remain” converging.If that graph continues its current trend, by the time we get to the referendum there is a chance that the betting will be mostly in favour of Brexit. Indeed, the bookies reported the other day a significant increase in betting for “leave”, thereby changing the odds again. I admit, the odds at the moment are mostly in favour of “remain” though.

  2. We work in these areas and Wales is by no means blue! Maybe the evidence is slightly skewed by the fact that most older people who are absolutely decided on voting out, don’t tweet.

    • That might seem the case, but the evidence suggests otherwise. The average age of someone who Tweets is 52. Indeed, younger people tend to avoid Twitter more than older people. I agree, though, that Twitter usage itself is not a perfect representation of the population. We’ll only find out if the data are correct when we get the results of the referendum.

  3. I live in Northumberland and have a night club there and most people in talk to want out, but show up as in on here.

    • Yes, there is bound to be some variation. The map is showing the whole of the area only, not individual towns. For instance, as I said in the article, the town of Reading is showing a considerable tendency towards staying, but other towns in Berkshire are not the same. As a result, Berkshire on the map ends up as neutral, even though Reading is significantly in favour of remain.

  4. well i live in Hull and i don`t know a single person who wants to remain .I think this map is about as accurate as a pisshead trying to hit a toilet with his wazz stream !

    • That’s a colourful image I’m trying not to think about too much…! But I take your point. As I said before, the feelings in one town may not reflect the feelings of the entire area on the map. So people outside the town of Hull might be more inclined to remain. However, it is only light blue on the map, showing there is a degree of influence from many people who want to leave.

  5. Mmm, not sure about the accuracy of this. Like Anya Jenkins above, we’re also pretty much bang in the middle of Wales and hardly ever encounter a Remainer, yet the map says Powys is solid blue for remain.

    • Yes, it does seem odd doesn’t it. However, one of the interesting psychological effects in many group studies is that somehow (we don’t know how) we tend to talk to people who all hold similar views (not necessarily as ourselves, but with one another). So, the people we tend to meet will tend to hold similar views, even if they are not the majority view. It is an interesting group psychology phenomenon.

  6. Strange how Scotland appears solid red. According to mainstream media the SNP were threatening another Scottish referendum if we left the EU, I assumed because the Scottish People might quite like to remain?!

    • The problem with Scotland is the vote counting that the SNP will be using to determine whether another referendum vote should take place.
      If the majority of Scots vote to ‘Remain’, with the rest of the UK swinging a ‘Leave’ vote, the SNP will have a mandate to call for a new referendum, with the option of Scotland then joining the EU as a single country, outside the UK.
      If a lot of Scots vote tactically for Leave, to try to force a referendum if the UK does a ‘Brexit’, even though they want to remain, the vote count might go against them in the total tally.
      Tricky call for the Scots, this one.

  7. Interesting even taking into account the nuances of the cohort – just reviewed #BREXIT using Keyhole.co and it would appear to show a similar result. It’s strange given how we wouldn’t be without our smartphones, expect delivery the day we buy and instant replies to messages, that people in general and more specifically those running campaigns appear so poor on the use and capitalisation of social media. Perhaps one camp is doing a better job on social media than the other at the moment!

    • The study appears to focus on the official hashtags: #StrongerIn #UKinEU #VoteLeave and #LeaveEU, so a rather limited sentiment analysis. Has anyone gone a little more indepth? And what of other widely used hashtags such as #REMAIN (which appears to be missed) and probably others?

  8. If you look at the Guardian newspaper website you will see a majority of comments are pro-Brexit, the Independent website comments are 99% Brexit and the Labour facebook page is 100% Brexit.

    Based on the above I think its very likely we will be leaving. The only ones who wish to Remain are the metropolitan elite and the hug-a-refugee brigade.

  9. I forgot to say, there is also a significant majority of Mirror website comments which are Brexit. I think the working class know that Remaining means more migrants to burden their schools, GP surgeries, hospitals, dentists, social housing and keep low-skilled wages low.

  10. By focusing on immigration, Brexit has found its only traction, since it has been exposed on every other issue. Whilst it is an important issue, It is not worth what will be lost should the tie with Brussels be cut and such people take over the political system. A demoralised working class is easy meat for the right wing Tories, and they will be easily persuaded to scapegoat Brussels for all their ills.

    I notice these rightists, when challenged over their £350million lie, move to an annualised figure of £10billion, which is a mere bagatelle in the context of the economy. Any big number to scare the vulnerable unschooled. As for this money being used in the NHS, can you imagine this from these people who are keen to privatise it??? The same old tactics Tories have always used to steal the working class vote.

    Brexit admit there will be a period of uncertainty, should they win. But it will be long enough for many middle aged people to lose their jobs and never find another one.

Comments are closed.

Cover page of free report

Weekly Online Business Advice

FREE

Get FREE advice to boost your online business EVERY

Saturday morning

And get this free booklet too

This site uses cookies

This website uses cookies to improve your experience with the site and to enable some functions to operates. Google Analytics is also used on this site. Please either accept or reject Google Analytics Cookies on this site.