Linguamatics Sorts Election Tweets

In the UK, text mining specialist Linguamatics is using natural language processing technology to analyse general election-related tweets and group those with the same meaning.

Cambridge-based Linguamatics uses a combination of search and text mining to enable organisations to extract facts, relationships and quantitative data from content such as scientific papers, news feeds, patents or internal reports.

The firm is currently using natural language-based querying to find and summarise tweets that have the same meaning, however they are worded.

To do this, it has adapted its 12E text mining software for real-time social media analysis, to uncover the wide-range of vocabulary used in tweets; using linguistics processing to collect and summarise the thousands of ways people have of saying the same thing.

After last week's preliminary leaders' debate, Linguamatics' data showed that 65% of twitterers who expressed an opinion said that Nick Clegg performed best, followed by Gordon Brown (21%), and then David Cameron (14%). These results contrasted with the immediate post-debate poll by Sun/YouGov, which put Clegg ahead at 51%, Cameron at 29%, and Brown at 19%.

Executive Chairman John Brimacombe said: 'For Twitter, we've demonstrated an objective way to detect real world opinion as it develops. This ability to filter huge volumes of text in real time has implications for decision-makers across the board.'

With headquarters in Cambridge, UK and US operations in Newton, MA, the firm is online at www.lingaumatics.com .

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