Sex Trafficking Detection with Ordinal Regression Neural Networks
This work addresses a critical issue for law enforcement agencies by automating the identification of trafficking leads from millions of escort ads, though it is incremental in method.
The paper tackles the problem of detecting sex trafficking in escort ads by proposing an ordinal regression neural network with a modified cost function, which significantly improves on the previous state-of-the-art on the Trafficking-10K dataset.
Sex trafficking is a global epidemic. Escort websites are a primary vehicle for selling the services of such trafficking victims and thus a major driver of trafficker revenue. Many law enforcement agencies do not have the resources to manually identify leads from the millions of escort ads posted across dozens of public websites. We propose an ordinal regression neural network to identify escort ads that are likely linked to sex trafficking. Our model uses a modified cost function to mitigate inconsistencies in predictions often associated with nonparametric ordinal regression and leverages recent advancements in deep learning to improve prediction accuracy. The proposed method significantly improves on the previous state-of-the-art on Trafficking-10K, an expert-annotated dataset of escort ads. Additionally, because traffickers use acronyms, deliberate typographical errors, and emojis to replace explicit keywords, we demonstrate how to expand the lexicon of trafficking flags through word embeddings and t-SNE.