The reported experiments focused on case building for combating human trafficking, where the investigator follows leads to expose organized activities, i.e., different escort advertisements that are connected and possibly orchestrated.
The authors’ “RedThread,” is an efficient solution for inferring related and relevant nodes while incorporating the user's feedback to guide the inference. The results of RedThread are interpretable, as they explain how the results are connected to the initial lead. The authors experimentally show that RedThread learns the importance of the different types and different pieces of evidence, while the former could be transferred between cases. (Published abstract provided)
Similar Publications
- Collection, Storage, and Use of Client Data: Considerations and Recommendations for Human Trafficking Service Providers
- Audit of the Office of Justice Programs Victim Assistance Funds Subawarded by the New Mexico Crime Victims Reparation Commission to The Life Link, Santa Fe, New Mexico
- Improving Collaboration Between Departments of Labor and Other Members of the Anti-Labor Trafficking Community