LONDON – Scientists have developed an algorithm-based system thatidentifies telltale signs in fake news stories could provide newsaggregator and social media sites like Google News with a new weapon in thefight against misinformation.

Researchers from the University of Michigan in the US who developed thesystem have demonstrated that it is comparable to and sometimes better thanhumans at correctly identifying fake news stories.

In a recent study, it successfully found fakes up to 76 per cent of thetime, compared to a human success rate of 70 per cent.

In addition, their linguistic analysis approach could be used to identifyfake news articles that are too new to be debunked by cross-referencingtheir facts with other stories.

Rada Mihalcea, professor at University of Michigan, said an automatedsolution could be an important tool for sites that are struggling to dealwith an onslaught of fake news stories, often created to generate clicks orto manipulate public opinion.

Catching fake stories before they have real consequences can be difficult,as aggregator and social media sites today rely heavily on human editorswho often can’t keep up with the influx of news.