Baylor professors use AI to identify online listings that lead to criminal activity

Published: Oct. 19, 2022 at 10:10 PM CDT
Email This Link
Share on Pinterest
Share on LinkedIn

WACO, Texas (KWTX) - Imagine a computer being able to identify a suspicious online listing just by the way it is written. Thanks to a new grant, two Baylor professors may help make that become a reality.

Computer science assistant professors Pablo Rivas and Tomas Cerny were awarded a $314,284 from the National Science Foundation. They are working with a team of researchers from other universities to stop sex trafficking and the sale of stolen car parts.

The team is testing out AI to identify how sites that sell goods, like Craigslist, could lead to these kinds of illegal activities.

“The team is trying to understand how people communicate on these sites, especially criminal organizations,” Rivas said.

Specifically, the team is researching the wording in listings from these sites and how they could lead to sex trafficking or the sale of stolen car parts. One day, they hope to equip law enforcement with the tech.

“Once you get the new lead, you suddenly connect the pieces of puzzle that wouldn’t make sense before, but suddenly you have many more perspectives to look at the same problem,” Cerny said.

Natural language processing (NLP) is a branch of computer science that helps computers better understand words the same way humans do. It’s not new technology, but researchers said it’s never been used in this way before.

“Now we can take this at a scale that is unprecedented, so that will yield a better understanding of how language works,” Rivas said.

Imagine the AI being able to detect something suspicious from misspelled words or even the emojis used in a post. That’s what the technology could accomplish.

“We’re hoping to look beyond these nuances and look to the potential of one post being flagged as human trafficking or a post that says this is an illicit car part,” Rivas said.

Undergraduate, graduate and PhD students are all involved in helping the Baylor professors with this project. Through the grant, the research project will run through April 2024