WACO, Texas (KWTX) — Imagine a computer that could identify a suspicious online listing just by the way it’s written. Thanks to a new grant, two Baylor professors could help make this a reality.
Computer science assistant professors Pablo Rivas and Tomas Carny have received $314,284 from the National Science Foundation. They work with a team of researchers from other universities to stop sex trafficking and the sale of stolen car parts.
The team is testing AI to identify how sites that sell goods, like Craigslist, could lead to this kind of illegal activity.
“The team is trying to understand how people communicate on these sites, especially criminal organizations,” Rivas said.
Specifically, the team is studying the wording of the listings of these sites and how they might lead to sex trafficking or the sale of stolen car parts. One day, they hope to equip law enforcement with the technology.
“Once you get the new lead, you suddenly connect the puzzle pieces that didn’t make sense before, but suddenly you have a lot more perspectives to look at the same problem,” Carny said.
Natural language processing (NLP) is a branch of computer science that helps computers better understand words in the same way humans do. It’s not a new technology, but the researchers said it has never been used in this way before.
“Now we can take this to an unprecedented scale, which will lead to a better understanding of how language works,” Rivas said.
Imagine AI being able to detect something suspicious from misspelled words or even emojis used in a message. This is what technology could accomplish.
“We’re hoping to look past those nuances and examine the possibility of a post being flagged as human trafficking or a post that says it’s an illicit car part,” Rivas said.
Undergraduate, graduate and doctoral students are all involved in helping Baylor professors with this project. Thanks to the grant, the research project will continue until April 2024
Copyright 2022 KWTX. All rights reserved.
#Baylor #professors #identify #online #listings #lead #criminal #activity