Tweetminster are attempting to use Twitter to predict the election outcome. A Japanese study last year precicted the outcome with 90% accuracy.
A group of online entrepreneurs are attempting to use Twitter to predict the election outcome. Tweetminster, a media utility that aims to make UK politics more open and social, is following the success of a Japanese study during last year’s general election which found that that in around 90 per cent of constituencies the most mentioned candidate on Twitter won the seat.
Analysis of 376 British seats since January 1st, 2009 gives Labour a slight lead of 35 per cent to 34 per cent over the Conservatives with a majority of 14 predicted. The Liberal Democrats are on 22 per cent and Others on 9 per cent. But the report is keen to outline that “assuming the same 10% margin of error of the Japanese study, the range of potential outcomes would also encompass various hung parliament scenarios with Labour short of seats”.
The report also predicts that:
• An important number of seats are being closely contested in the South West between the Conservatives and Liberal Democrats;
• The Green party may prosper in Brighton and Norwich;
• Support for the SNP is declining while Angus is a particular “race to watch”; and
• The Conservatives will perform positively in the East Midlands while Labour and the Liberal Democrats will “perform better in London than recent polls have shown”.
Alberto Nardelli, Co-founder of Tweetminster, said:
“While we have a 90% accuracy rate benchmark from a similar study in Japan, we are keen to stress that this exercise isn’t a poll, it’s an experiment into predictive modelling and we cannot speculate on the level of accuracy of these predictions at this stage.
“In fact, the whole point of the experiment is to compare mentions and word-of-mouth on Twitter with election results to determine if a correlation between the two actually exists.”
John Rentoul on the Independent Minds blog suggests a firm “No”
Leave a Reply