MIT grad student builds online 'lie detector'

The next time politicians or other officials make self-serving or suspicious claims, an Internet equivalent of “truth goggles” may soon be set up to flag such claims.

 

Massachusetts Institute of Technology (MIT) Media Lab graduate student Dan Schultz is working on software that can highlight false claims in online articles.

 

“I’m very interested in looking at ways to trigger people’s critical abilities so they think a little bit harder about what they’re reading ... before adopting it into their worldview ... I want to bridge the gap between the corpus of facts and the actual media consumption experience,” Schultz said in an interview with the Nieman Journalism Lab.

 

Among the potential abilities of the software are to flag suspicious sentences, and to offer more “factual” alternatives.

 

But Schultz stressed his software will not be able to determine lies from truth on its own, but merely help humans do so.

 

His software relies on a database drawn up by PolitiFact’s researchers.

 

“It’s not just deciding what’s bullshit. It’s deciding what has been judged. In other words, it’s picking out things that somebody identified as being potentially dubious,” he said.

 

Schultz’s work explores natural language processing, in which computers learn to talk the way humans do.

 

The Nieman Journalism Lab said Schultz’s truth goggles will be made open-source once finished in 2012, although PolitiFact, the database it will rely on, is not.

 

But Schultz said more sources “would help people break away from their filter bubble,” and people “would be exposed to opinions they hadn’t seen before.”

 

“The ultimate goal is to enable intelligent conversations about contentious issues,” he said. — TJD, GMA News