Boffins developing Twitter lie-detector so journalists can tell if a tweet is telling the truth

University boffins are developing a lie-detector for Twitter that will allow journalists to determine whether a message is truthful.

Researchers in five universities have received £3.5 million in funding from the European Union to create the verification software.

The aim of the project is to create a real-time system for verifying the accuracy of messages on the popular social media website.

According to The Times, researchers across the continent are collaborating on the system called Pheme, after a Greek mythological character renowned for spreading gossip.

Researchers hope that bogus Tweets could be quickly identified to stop the spread of panic, particularly during fast-moving events such as the London riots.

Lead researcher of the project Kalina Bontcheva from the University of Sheffield’s engineering department told The Times: “People do believe things they hear on the internet. In critical situations, you can instead show reliable information or alert the authorities before things get out of hand.”

The developers hope the system will be able to alert Twitter users about possible threats in retweeting bogus information such as the false rumours surrounding Lord McAlpine.

The system will seek to identify accounts set up especially to disseminate false information or automated robot tweeters.

Twitter users will be ranked according to their reliability with increased value attached to the accounts of verified news organisations.

It is understood that Pheme could be operational within 18 months.





Press Gazette's must-read weekly newsletter featuring interviews, data, insight and investigations.

No comments to display

Leave a Reply

Your email address will not be published. Required fields are marked *