Human trafficking is a huge problem, morally, economically and legally. One reason it’s so hard to fight it is that it’s a hidden crime. Largely gone are the days when prostitutes hang out on darkened streets. Instead, a girl or woman is pimped out via the internet. Even more difficult, traffickers often use the Deep Web:
The term “Deep Web,” refers to the “deeper” parts of the web that are accessible, but are considered hard to find because they aren’t indexed by regular search engines. Information on the Deep Web can be indexed, but only using complex search algorithms that have the ability to break down certain barriers.
At the University of Southern California, a team in the Viterbi Information Sciences Institute (ISI) has figured out a way to search big data, and catch traffickers. Rather than having law enforcement go through one “ad” after another for escorts and “dancers,” the ISI team
created a tool that combs through escort ads—mining, decoding, and organizing the relevant data into an enormous but easily searchable database.
The tool, called DIG (for “Domain-specific Insight Graphs”), allows officers who are searching for a missing child who is believed to be trapped in the escort industry to search by phone number, location, alias—even by photo—and pin down a way to reach them.
“The internet contains seemingly limitless information, but we’re constrained by our ability to search that information and come up with meaningful results. DIG solves that problem,” says Szekely, research associate professor at ISI.
DIG doesn’t require extensive training to use, and it can make new connections and detect patterns on its own as its data grows. The ISI team believes it can be updated quarterly, which will give law enforcement much more timely information.