As society turns to social media as their main information source, researchers from the University of Melbourne have found a way to help determine the truth from the lies on Twitter.
Professor Stephan Winer and Marie Truelove from the Melbourne School of Engineering have developed a framework to assess whether a tweet is a witness account from a first-hand experience or not.
“The most obvious starting point is to determine whether a tweeter is at an event using their the georeference, or location information found in the metadata of some tweets,” Ms Truelove said.
“But only a small fraction of users turn this option on. To identify more sources of evidence we turn to the content of the tweet itself – the text and pictures.”
The combination of the text (statements like smoke in the sky for a bushfire), images (of the smoke rising above the house) and location information (geotags from the relevant town or suburb) all work together to build a case for the user being a credible witness.
But Ms Truelove said there were still challenges in determining credible witness.
“Conflicting evidence such as a post of an image taken from an event shown on a TV screen or tweets of an event that didn’t occur are analysed to test whether the tweeter is at the event and reporting their direct observations,” said Ms Truelove.
“Our framework uses machine learning to automatically investigate the different sources within the tweets, including those posted by the user prior and after.
“Retweets are removed and if multiple evidence is still available for a single tweeter, it is assigned with a credibility measure, from low to high.”
While still in early development, Ms Truelove said this framework undoubtedly would be an asset to journalists around the world.
“If news organisations in particular had access to a frame work like ours to assess these kinds of tweets purporting to be witness accounts, we could all trust our news a little bit more.”