This is the first post on the Language Spy blog. Welcome!
Of course, a web site like this one doesn't just come in to being spontaneously, behind this site there lies a lot of data and a lot of work. What began in the last decade when Tony Blair had only just vacated Number 10 has turned from a personal side project on a laptop into a huge cloud-hosted website. The first incarnation of the political language corpus ran on a MySQL database and took minutes to answer a query, this website uses a cloud file based database and answers queries in a fraction of a second.
As this post is being written the UK is in the run-up to a general election. We hope that the tools on this site will help people get a fresh insight into the campaign that might not be obvious from the news. With five or six mainland parties standing a good chance of scoring seats it's likely that this election will be one of the most exciting for many decades and will remain frustratingly impossible for the armchair pundit to call the result.
Looking forwards, next year sees the United States presidential election. With its endless campaign it's the gift that keeps on giving for political enthusiasts, we're looking forward to what insights the Language Spy corpora can give us. Clinton, Biden, Perry, Bush, and a host of other names that haven't made the news yet on this side of the Atlantic, we'll see what they bring us in the next 18 months.
Of course, Language Spy won't be standing still either. Political corpus analysis is our launch product, but there are plenty more applications of language technology to be produced. The front page of this site says Language analysis for everyone, and that sums up our mission nicely. We hope you'll stick around.
Tags for this post: technology