Newspaper article Pittsburgh Post-Gazette (Pittsburgh, PA)

Thinking like Us Cmu Researchers Are Building a Model to Predict Human Behavior, Which Could Save Lives One Day

Newspaper article Pittsburgh Post-Gazette (Pittsburgh, PA)

Thinking like Us Cmu Researchers Are Building a Model to Predict Human Behavior, Which Could Save Lives One Day

Article excerpt

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.

In the future, SocialSim could help explain why you're seeing articles from the Pittsburgh Post-Gazette in your news feed, rather than from a website that you don't recognize. Or, Mr. Lebiere pointed out, it could even help the U.S. government understand how foreign enemies use the internet to spread rumors.

Smart simulations

Mr. Lebiere's team is developing the simulation for the SocialSim project. That is, they're building a model that mimics human behavior, which they can then feed a scenario and examine the results (no humans required).

Imagine having a computer program that could analyze any situation and how the general public will respond - like a change in the Facebook algorithm. That's the model.

To create it, the team will build a "cognitive architecture," or reproduction of how humans think.

"[Cognitive architectures] are meant to represent, at some level, the computational processes that go on as we perceive the world, as we act on the world, as we make decisions and as we plan to solve a problem," Mr. Lebiere said.

One successful example is CMU's "Act-R" cognitive architecture, which was completed for release in 2014. It essentially breaks down the human mind into a series of operations.

Act-R has been used to create models in hundreds of scientific publications, and it's been applied for use in cognitive tutors that mimic the behavior of a student - personalizing his or her curriculum and instructions based on any difficulties the pupil is experiencing. …

Search by... Author
Show... All Results Primary Sources Peer-reviewed


An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.