In the US, an organisation called the Sunlight Foundation's has extended the Churnalism concept based on a UK site with the same name, to detect plagiarism and rehashed PR.

At present it works with only a relatively small number of PR sources, but could be extended as demand (and funds) permit.

Here at GXpress – where the b******t filter has been honed over years, hopefully cutting the bunkum from industry PR – we think it’s a great idea. Especially as brands work increasingly to infiltrate editorial columns.

Churnalism is driven by open-source search engine technology dubbed SuperFastMatch, developed by the Media Standards Trust which backed the original Churnalism site. Sunlight Foundation says it will work with MST to adapt the site for a US audience and build browser extensions with similar functionality.

The app searches the text you enter against a large corpus of press releases and determines the best matches.

Sometimes, exact fragments will match that are clearly not plagiarism. These often include expanded organisational names (such as The United States House of Representatives) or boilerplate copy about a particular company that is usually appended to the end a press release, it says. In order to filter out uninteresting matches and provide the best user experience, Sunlight uses a relevancy ranking derived from the total character overlap and the density of that overlap.

The source code for the project is on the Sunlight Labs Github page. Sunlight also plans to make its PR database available as a standalone API. Major sources include PRNewsWire, PR NewsWeb, MarketWire, EurekaAlert, Congressional Leadership, The White House, Trade Organisations, Fortune 500 Companies, Nonprofit Research Institutes and Thinktanks.

Here’s the Sunlight video explaining how it works: