On the Challenges of Creating Datasets for Analyzing Commercial Sex Advertisements to Assess Human Trafficking Risk and Organized Activity

TL;DR

This paper discusses the difficulties in creating datasets for analyzing commercial sex ads related to human trafficking, proposing an automated, reproducible methodology to aid researchers in developing effective datasets for detection.

Contribution

The authors introduce a novel automated and reproducible methodology for building large-scale datasets from commercial sex advertisements, addressing key challenges like data scarcity and privacy.

Findings

Analyzed five million advertisements to demonstrate methodology effectiveness.

Identified key challenges in dataset creation for sensitive domains.

Provided a streamlined process to improve dataset quality and reproducibility.

Abstract

Our study addresses the challenges of building datasets to understand the risks associated with organized activities and human trafficking through commercial sex advertisements. These challenges include data scarcity, rapid obsolescence, and privacy concerns. Traditional approaches, which are not automated and are difficult to reproduce, fall short in addressing these issues. We have developed a reproducible and automated methodology to analyze five million advertisements. In the process, we identified further challenges in dataset creation within this sensitive domain. This paper presents a streamlined methodology to assist researchers in constructing effective datasets for combating organized crime, allowing them to focus on advancing detection technologies.