Introducing Tweetminster's Election Platform
Tweetminster now follows over 400 politicians on Twitter, 100s of news sources, commentators and influencers, and the ‘sample size’ that powers Tweetminster Search is now nearing 10,000 individuals. Over the past few weeks we have also experimented around live events and launched a real time research study that is fed from across Twitter.
These are exciting times for us.
Today, we’re delighted to announce the launch of Tweetminster’s General Election 2010 platform.
The page consolidates existing Tweetminster functionality, Search (to find relevant tweets and associated trends) and our Find Your MP/PPC on Twitter tool, alongside a series of new features:
- A real-time sentiment ticker, tracking sentiment for around the main parties and leaders (especially interesting during the upcoming TV debates). We’ve also tweaked our existing sentiment score, shifting from a -100 to +100 range to a 0-5 - we believe this makes it easier to understand trends as they evolve in real time.
- Tweetminster Predicts - our predictive modelling experiment that aims to study the correlation between word-of-mouth and election results. We will be updating the figures weekly, and then daily in the final stretch to election day.
- A campaign map that visualises where the parties are campaigning right now, a regional breakdown of tweets and a livestream of all the tweets from candidates, news sources and key influencers.
The election page is live at tweetminster.co.uk Alongside our core site, we’re pleased to be collaborating with leading industry players to complement their election coverage.
Posted at Thu, Apr 1st 2010, 14:30
Tweetminster Daily - March 31 2010
The Tweetminster Daily is a summary of the day’s top political stories and analysis around UK Politics. The summary isn’t curated or editorially controlled, but entirely built using data around the most shared and clicked on links on Twitter.
Issue 39 - 31/03/2010 - 17:00
Today’s most shared stories on Twitter around UK Politics:
- Does he have what it takes?
- Tony Blair speech - as it happened
- Merkel set to snub Cameron on UK visit
- Today’s damning letter from the stats watch-dog to Gordon Brown
- The new Digital Economy Bill clause
- David Cameron promises to create neighbourhood army
- If Twitter is right, Labour is set to win the election
- Lib Dems target Labservatives with guerilla marketing campaign
- Labour MP’s motion to subject Digital Economy Bill to full debate
Posted at Wed, Mar 31st 2010, 17:12
Can word-of-mouth predict the General Election result?
The forthcoming General Election is probably going to be one of the closest in recent UK history, with the pollsters suggesting various hung parliament and minority Labour or minority Conservative government scenarios. During the General Election campaign, Tweetminster is conducting an experiment around whether activity on Twitter correlates to electoral success.
Our inspiration for this experiment comes from last year’s General Election in Japan, when a group of software engineers and PhD graduates from Tokyo University undertook a study analysing the correlation between ‘online buzz’ and election results. The aim of the study was to assess if word-of-mouth mentions of candidates could help to predict which ones would be successful. The study found that in a majority of constituencies the most mentioned candidate won the seat (see References below).
We thought it would be interesting to run a similar experiment to the Japanese study in the UK using Twitter. From now until the election we will be tracking the most mentioned (i.e. posts and conversations about) constituencies and candidates on Twitter and using this data we will try to map the correlation between buzz, word-of-mouth and the eventual election results through a predictive model.
Today, to kick-off the study, we’re publishing a starting set of findings and the methodology that we’ll be adopting.
This paper sets out the initial findings of our experimental model, which we will update as the campaign proceeds. At this stage, our model suggests that the overall election result could see a small Labour majority or a hung Parliament, with the closely-fought contest between the Liberal Democrats and the Conservatives in a number of marginals in the South West tilting towards the Lib Dems; with Labour and the Liberal Democrats performing better in London than recent polls have shown; with declining SNP support in Scotland; and with the role of other parties in key seats all influencing factors in shaping our predictions.
Initial top-line predictions include an analysis of key target seats, a top-line party breakdown based on the most mentioned candidates in the 376 constituencies represented on Twitter - CONSERVATIVES 34%; LABOUR 35%; LIBERAL DEMOCRATS 22% OTHERS 9% - which, assuming margins of error, would encompass various hung parliament scenarios with Labour short of seats to a Labour majority of 14 seats.
Our data set is fed from all the constituencies represented on Twitter:
1. Constituencies with a candidate using Twitter
2. Frequently mentioned constituencies
3. High profile constituencies, i.e. key marginals and cabinet/shadow cabinet members’ constituencies that are mentioned on Twitter.
The study will be a dynamic analysis - we will update the predictions and track the variations in predicted election results as polling day gets closer, allowing us to see if the passage of time affects any significant shifts in predicted outcomes. For example: Will the Leader’s TV debates in mid-April make a difference to today’s predictions?
As discussion intensifies towards the election we expect to see the model reflect any changes in the balance of online buzz.
Two million tweets (and counting) are being processed and analysed for this study. The data set will be updated as new candidates join Twitter during the course of the campaign, findings and variations released throughout the campaign and the final report will be published after the election.
Please note that the scope of this exercise isn’t to compete with polling methodologies - it is an experimental study that aims to use predictive modelling around a dynamic data set to determine if there are correlations between word-of-mouth on social media and election results. All predictions are made on an experimental basis and the reliability of the method for predicting election results will be assessed once the study is completed.
Update - our week two updates have been released. The paper has also been updated accordingly.
Posted at Tue, Mar 30th 2010, 09:00
Who 'won' askthechancellors?
With a total of 12,250 tweets (averaging 4.1 tweets per second) #askthechancellors was the second most tweeted event around UK politics.
The expectations were great and the frequency of tweets was high throughout the evening - the event delivered. But who won?
We believe that the following data points if looked at holistically can help to inform this question:
- The majority of tweets were about the three participants, and less so about the topics they were debating.
- George Osborne was by far the most mentioned of the three. He was the focus of attention before and during the debate. A misspelt “George Osbourne” trended in the UK - this implies that a large number of tweets came from many people who don’t usually tend to tweet about politics and who are not supporters of the Conservative party.
- Sentiment around the three participants started at +8 for Vince Cable, +4 for Darling and +1 for Osborne. It ended at +5 (-3) for Cable, +1 (-3) for Darling and 0 (-1) for Osborne.
- The key metric here are variations - as they are an indicator of performance vs expectation.
Posted at Tue, Mar 30th 2010, 07:47