The social networking site can learn a lot about you from even that smallest social interaction.
Researchers from the University of Cambridge designed a simple machine-learning system to predict Facebook users' personal information and traits based solely on which pages they had liked, according to a report.
"We were completely surprised by the accuracy of the predictions," Michal Kosinski, lead author on the paper in PNAs, said to New Scientist.
Kosinski and his colleagues built the system by scanning likes for a sample of 58 000 volunteers, and matching them up with other profile details such as age, gender and relationship status.
He also matched up those likes with the results of personality and intelligence tests the volunteers had taken.
The team then used their model to make predictions about other volunteers, based on their likes.
Photo Courtesy of Flickr.com, username Sean MacEntee