TRAFFIC BOARD : Digital Spatio-Temporal Pinboard for Human Trafficking Detection
Catalina Vajiac, Duen Horng, †. Chau, Andreas M. Olligschlaeger, Pratheeksha Nair, Meng-Chieh Lee, M. Cazzolato, Reihaneh Rabbany, Christos Faloutsos
Abstract
— Practitioners can detect human sex trafficking (HT) in online escort websites by analyzing both the text and connections between metadata (i.e. contact information) throughout time of suspicious clusters of connected ads. Previous attempts at visualizing these graphs have suffered from the hairball effect, as certain portions of the graph are densely connected. Given a group of ads with shared metadata, how can we interactively visualize connections between metadata and how they change over time? T RAFFIC B OARD combines graph compression techniques and interactivity to enable practitioners to investigate suspicious metadata and their connections throughout time, as well as their geographic spread