ShareThis Page

CMU software eases task of mining prostitution ads

| Saturday, Jan. 31, 2015, 9:00 p.m.

Carnegie Mellon University researchers have developed software that allows police departments to mine online ads offering prostitution services.

Traffic Jam gives police a rapid way to sort sex ads, spotting indirect language that may suggest sex trafficking, or grouping ads with similar language that may have been written by the same person.

The software could be a boon to officers investigating trafficking who manually check ads, said Artur Dubrawski, director of the Auton Lab at CMU and a lead developer of the program at the university's Robotics Institute.

Auton Lab research analyst Emily Kennedy said more than 100 sites are commonly used in sex trafficking. The Tribune-Review found in its search dozens of ads posted daily on sites such as the Pittsburgh-area page of Backpage.com.

“That creates a massive stream of data coming in. If you are local law enforcement, using the data takes time. We realized that the quickest way to help victims was to support law enforcement,” Dubrawski said.

More than 400 people with 35 agencies — from police to prosecutors to nonprofits specializing in victim services — have trained to use Traffic Jam, including many in the Pittsburgh area, said Kennedy.

Dubrawski would not say which Western Pennsylvania agencies are testing the product, but noted one recent success: Police in Modesto, Calif., used Traffic Jam to search for ads posted by an alleged sex trafficker they had in custody. Using the software's search engine, Modesto Detective Darren Ruskamp said, he searched multiple websites at once using key terms. It identified places where the suspect, called “Big O,” had taken women to offer their services.

He was convicted under federal laws prohibiting the transport of people across state lines for the sex trade, Ruskamp said.

“I'd searched for eight-plus hours,” Ruskamp said about individually scanning popular sites for evidence. “Within about 10 seconds, I'd located numerous ads by him.”

Most victims are women

Traffic Jam began about three years ago when Dubrawski, Kennedy and Jeff Schneider, the other lead researcher, decided to apply computer science and machine learning to unraveling online sex trafficking. They released a prototype at the beginning of 2013, said Kennedy. The Defense Advanced Research Projects Agency, or DARPA, rewarded their initial work with a three-year, $3.6 million grant.

Through DARPA's Memex program, an initiative to develop better Internet search mechanisms, the team can continue to develop Traffic Jam and other tools, including those that can mine the Deep Web, pages often missed by common search algorithms that could contain information about the drug trade or other illicit activities. The grant will pay researchers to develop and test their work.

Statistics about sex trafficking in the United States vary according to the source, but the National Human Trafficking Resource Center in Washington says 82 percent of calls, emails and tips to its hotline from victims and survivors of sex trafficking come from women.

A report from the Arizona State University School of Social Work says the Internet plays a big role in prostitution because its anonymity offers protection.

One town's problem

Moon, a town of 25,000 near Pittsburgh International Airport, has 17 hotels. Police Chief Leo McCarthy said online ads and airport travel play a huge role in sex trafficking within town. He has one undercover detective who specializes in prostitution stings and said the detective must sort through ads to find perpetrators targeting Moon. They are not among the testers of Traffic Jam.

Many victims of sex trafficking are women who fly into town for a few weeks with a handler, make appointments through online ads, work through the hotels and leave, McCarthy said.

His officer arrests an average of 70 prostitutes and their pimps each year. Access to software that eases the search could lead to more arrests, McCarthy said.

Some cases are prosecuted in Allegheny County; others are turned over to the FBI, McCarthy said, especially those involving interstate travel, missing teens and adults or women who tell the detective they are working to pay off debts. He said the FBI is better equipped to help them get out of the business.

“Almost all the women who come here, they have a story. They definitely have had a hard life and would like to get out of it,” he said.

Megha Satyanarayana is a Trib Total Media staff writer. Reach her at 412-320-7991 or megha@tribweb.com.

TribLIVE commenting policy

You are solely responsible for your comments and by using TribLive.com you agree to our Terms of Service.

We moderate comments. Our goal is to provide substantive commentary for a general readership. By screening submissions, we provide a space where readers can share intelligent and informed commentary that enhances the quality of our news and information.

While most comments will be posted if they are on-topic and not abusive, moderating decisions are subjective. We will make them as carefully and consistently as we can. Because of the volume of reader comments, we cannot review individual moderation decisions with readers.

We value thoughtful comments representing a range of views that make their point quickly and politely. We make an effort to protect discussions from repeated comments either by the same reader or different readers

We follow the same standards for taste as the daily newspaper. A few things we won't tolerate: personal attacks, obscenity, vulgarity, profanity (including expletives and letters followed by dashes), commercial promotion, impersonations, incoherence, proselytizing and SHOUTING. Don't include URLs to Web sites.

We do not edit comments. They are either approved or deleted. We reserve the right to edit a comment that is quoted or excerpted in an article. In this case, we may fix spelling and punctuation.

We welcome strong opinions and criticism of our work, but we don't want comments to become bogged down with discussions of our policies and we will moderate accordingly.

We appreciate it when readers and people quoted in articles or blog posts point out errors of fact or emphasis and will investigate all assertions. But these suggestions should be sent via e-mail. To avoid distracting other readers, we won't publish comments that suggest a correction. Instead, corrections will be made in a blog post or in an article.