Artificial intelligence may be able to predict the political and religious views of social media users - even if they never post anything.
Analysis of who Twitter users follow and what they like on the platform are a more accurate representation of their opinion that what they themselves write, according to a new study.
Computer scientists from the University of Edinburgh examined more than 2,000 public Twitter accounts to show how social media data can reveal a person’s views on issues including atheism, feminism and climate change.
They found users' networks and the way they engage with content provide a better gauge of their views than existing methods, which currently assess the text of their own posts.
Combining the two approaches provides the most accurate prediction, the team says, with a success rate of almost 75 per cent.
Researchers say the findings highlight a need for improved privacy measures to prevent publically available data being used to infer people’s personal views.
They added having access to this data could enable malicious users to target people with fake information about contentious topics.
The new approach means that for the first time the views of people who never post on social media, known as 'silent users,' can be accurately predicted.
Around 60 per cent of social media users aged between 18-34 indicated they were prepared to quit social media for one month, a survey by the Royal Society for Public Health found in July, while an additional 40 per cent were concerned about the amount of time they spent of platforms.
Dr Walid Magdy, of the University of Edinburgh’s school of informatics, who led the study, said: “Social media users are highly vulnerable to having their personal views predicted, without them even discussing the topics online. This shows the power of artificial intelligence when it is applied to big data.”
The research will be presented at the ACM Conference on computer-supported cooperative work and social computing (CSCW) in November in Austin, Texas.
Co-author Abeer Aldayel added: “Our study highlights a need to develop regulations and counter algorithms to preserve the privacy of social media users.”