THINKING LIKE US CMU researchers are building a model to predict human behavior, which could save lives one day

Pittsburgh Post-Gazette

Facebook has developed a number of hypotheses about human behavior, using its popular news feed as a test bed and the underlying algorithm as an independent variable that changes multiple times per year.

In the latest experiment, the Menlo Park, Calif.-based technology company announced a shift to focus on local news more. Now the question is: How will the dependent variables examined — all of us, effectively guinea pigs — react?

According to a Carnegie Mellon University professor researching the spread of social information, Facebook hasn’t a clue.

Not understanding how or why the news is reaching us can be problematic, as illustrated by the fake news epidemic. And the problem scales: In 2016, the Pew Research Center found 62 percent of adults relied on social media to digest the news.

“Maybe they have better theories than I’ve heard, but [Facebook is] largely operating by trial and error,” said Christian Lebiere, a research psychologist in CMU’s Dietrich College of Humanities and Social Sciences and the principal investigator for CMU’s portion of a federally funded project called SocialSim.

The project will develop technologies to create an accurate, scaled simulation of online social behavior, funded by a $6.7 million grant over four years from the Defense Advanced Research Projects Agency (DARPA) in November.

The team is led by Virginia Tech researchers, supplemented by three CMU experts and others at Stanford, Claremont, Duke, Wisconsin and the University of Southern California.