Identification and Detection of Human Trafficking Using Language Models

No ratings

Presented at EISIC 2019 by

Zhu Jessica

Lin Jones

In this paper, we present a novel language model-based method for detecting both human trafficking ads andtrafficking indicators. The proposed system leverages language models to learn language structures in adult serviceads, automatically select a list of keyword features, and train a machine learning model to detect human traffickingads. The method is interpretable and adaptable to changing keywords used by traffickers. We apply this methodto the Trafficking-10k dataset and show that it achieves better results than the previous models that leverage bothad text and images for detection. Furthermore, we demonstrate that our system can be successfully applied todetect suspected human trafficking organizations and rank these organizations based on their risk scores. Thismethod provides a powerful new capability for law enforcement to rapidly identify ads and organizations that aresuspected of human trafficking and allow more proactive policing using data.