UK Election: Do Tweets Spell Success?

In the UK, political polling group Tweetminster is analysing around two million Tweets, as part of an experiment to determine whether activity on Twitter correlates to electoral success in May's general election.

Tweetminster, which was founded by social media specialist Alberto Nardelli , describes itself as a service that connects the public to the politicians, commentators and news that 'shape UK politics'.

From now until the election, the group will be tracking the most mentioned constituencies and candidates on Twitter, and using this data will attempt to map the correlation between buzz, word-of-mouth and the eventual election results through a predictive model.

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 study found that in a majority of constituencies, the most mentioned candidate won the seat.

Initial top-line predictions include an analysis of key target seats and a top-line party breakdown based on the most mentioned candidates in the 376 constituencies represented on Twitter. To date, shares of the vote are Conservatives 34%; Labour 35%; Liberal Democrats 22%; and others 9%, which Tweetminster says would encompass various scenarios from a hung parliament to a Labour majority of 14 seats.

The group will update the predictions and track the variations in predicted election results as polling day approaches, and will also examine the leaders' TV debates in mid-April to see if they make a difference to predictions.

Two million tweets are being processed and analysed for the study, and the data set will be updated as new candidates join Twitter during the course of the campaign. Findings and variations will be released between now and election day, and the final report will be published after the election.

However, Tweetminster cautions that the scope of the exercise is not to compete with polling methodologies, and describes it as an 'experimental study' that aims to use predictive modelling to determine if there are correlations between word-of-mouth on social media and election results.

Will they admit it if there are none and it's all pretty random? We await results with baited breath.

Web site: www.tweetminster.co.uk .

All articles 2006-23 written and edited by Mel Crowther and/or Nick Thomas, 2024- by Nick Thomas, unless otherwise stated.