WILLIAMSBURG, Va. (AP) — Computer scientists at William & Mary say a new algorithm can predict political leanings among Twitter users.

University spokesman Joseph McClain says the program examined user networks — not tweets.

Ph.D. student Cheng Li said political polarization is even more pronounced in social media than in real life.

“A left-leaning person will never see news from a source that is right of center, even though it might be correct and make sense, because their friends don’t share this kind of news,” said Li.

Then-candidate Donald Trump’s tweets dominated social media.

Li said reactions to Trump-related tweets were highest at both political extremes.

“Trump reactions make a nearly perfect U-curve,” Li said. “There are large reactions from the far right and large reactions from the far left. And it goes down pretty evenly on both sides to a low point where the middle-of-the-road is.”

Li worked on the project with professor Zhenming Liu. They checked the accuracy of their work with the help of political science professor Jaime Settle.

The study involved 12 million Twitter users in October and November around election time.

WTOP’s Neal Augenstein contributed to this report.