AI can predict social media users’ opinions
Who Twitter users follow and what they like are more accurate predictors of their views than what they write, a study suggests.
People’s opinions on politics, religion and other topics likely to provoke debate can be predicted even if they never post anything about them online.
Researchers say the findings highlight a need for improved privacy measures to prevent publically available data being used to infer people’s personal views. Having access to this data could enable malicious users to target people with fake information about contentious topics.
Computer scientists from the University 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 that people’s networks and the way they engage with content provide a better gauge of their views than existing methods, which assess the text of users’ own posts.
Combining the two approaches provides the most accurate prediction, the team says, with a success rate of almost 75 per cent.
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.
Their new approach means that for the first time the views of people who rarely – or never – post on social media, the co-called silent users, can be accurately predicted.
Our study highlights a need to develop regulations and counter algorithms to preserve social media users' privacy.
The research will be presented at the ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW) in November in Austin, Texas.