SMU team creating a data warehouse to fight human trafficking

Human trafficking is often described as a hidden crime. People forced or coerced into commercial sex work may be the most obvious victims, but human trafficking can incorporate forced labor of all kinds, debt bondage – even forced marriage. 

The U.S. Department of State estimates more than 27 million people are trafficked worldwide at any given time. Trafficking does leave a trail, but it can be spotty because information about it comes from many sources, not all of them reliable. 

A team at SMU is working to make that trail easier to follow, developing a federally funded data warehouse to centralize and share data collection to aid in both prosecution of criminals and victim support. A uniquecomponent of this project includes the development of a video game called “Dark Shadows” to help researchers extract and “clean” relevant human trafficking information from U.S. Department of Justice press releases for entry into the database.   

The goal is to give researchers, law enforcement, and others devoted to anti-trafficking a single, secure place where they can store data, analyze trends in forced labor and sex trafficking, and collaborate with other anti-trafficking experts.  

“Human trafficking data exists, but datasets are often siloed by individuals and organizations, which decreases the useability of the data,” said Beth Wheaton-Páramo, the economist leading the SMU human trafficking research team. “Many of these datasets are based on case studies, meaning they describe a very specific geographic or socioeconomic area of human trafficking that may not provide a full picture of what is happening across the nation.” 

With the help of SMU’s high-performance computing capabilities, law enforcement and others devoted to anti-trafficking work will be able to utilize the datasets housed in the data warehouse to analyze trends in forced labor and sex trafficking much faster than the months it would take for a single investigator to acquire the information from press releases, case studies and other sources. Data warehouse users will have credentialed access to a secure online dashboard to identify trends in human trafficking across datasets in a way that was previously impossible. 

Wheaton-Páramo notes that SMU offers the advantage of neutrality in sharing the data, breaking down the potential for rivalry that can interfere with information sharing. 

Initial funding for the data warehouse is coming from a $1.187 million grant from the U.S. Department of Justice’s National Institute of Justice intended to improve the functionality of the criminal justice system, prevent or combat juvenile delinquency, and assist victims of crime. The project includes a study of the relationship between economics and human trafficking – both for victims and perpetrators – and the projected cost of failing to address this type of crime. . Wheaton-Páramo, author of 2019’s The Economics of Human Rights, is working with Raanju Sundararajan, SMU assistant professor in statistics, for the cost analysis and an examination of spatial and temporal patterns in human trafficking data. 

VIDEO GAMERS WILL BE PART OF THE RESEARCH TEAM 

SMU Guildhall, the university’s graduate program for video game design, has a major role to play in ensuring that accurate, useful data gleaned from Department of Justice press releases – such as perpetrators’ names and crime locations – is shared through the warehouse.   

Existing artificial intelligence models can make mistakes. For instance, an algorithm scanning a DOJ press release might incorrectly label a victim named “Madison” as the name of the city where a crime occurred.  

Computer scientist Corey Clark, who is Guildhall’s deputy director for research, and SMU postdoctoral researcher Steph Buongiorno are creating a video game called “Dark Shadows,” based off the popular game “Fallen Shadows.” In “Dark Shadows,” each player acts as an investigator of an imaginary crime and, in finding clues, will organize actual human trafficking data by proxy.  

As they play the game, video players will teach the AI driving the program to make fewer mistakes, as well as how the algorithm can make connections between different press releases for possible leads in an investigation. This method is known as “human-in-the-loop AI.” 

Video gamers will not be given any information that would allow them to find a human trafficking victim or perpetrator. And Clark stressed that the game doesn’t give players or a computer program the ability to direct an actual investigation. The game is a tool – not a replacement for law enforcement. 

Clark has also used video games to enhance data-driven research to speed up the discovery of new cancer-fighting drugs, along with other applications. 

Skip to content