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. For instance, it accounts for someone following a right-leaning news organization or a left-leaning one.
Ph.D. student Cheng 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.
The work appeared to confirm a trend toward increasing political polarization in the United States. A test run also showed that 10 percent of rightmost users accounted for much of the “fake news” traffic.
Copyright 2017 The Associated Press. All rights reserved. This material may not be published, broadcast, rewritten or redistributed.