Proceedings

Detecting Illicit Massage Businesses by Leveraging Graph Machine Learning

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. AI and Social Good. Pages 9647-9655.

https://doi.org/10.24963/ijcai.2025/1072

Abstract

Thousands of Illicit Massage Businesses (IMBs) are estimated to be operating in the United States by disguising themselves as legitimate establishments while exploiting trafficked workers, harming both the victims and the massage industry. The increasing digital presence of these illicit businesses presents an opportunity for detection, a crucial task for law enforcement and social service agencies aiming to disrupt their operations. Our research leverages user-generated business reviews from Yelp.com, enriched with data from multiple sources, including RubMaps.ch, U.S. Census records, GIS data, and licensing information. We present a feasibility study of developing a graph convolutional network (GCN) for a novel application and exploring its benefits and drawbacks in identifying IMBs. The novelty of our approach lies in its ability to link and analyze businesses, reviews, and reviewers within a heterogeneous network and employ a relational GCN to capture their complex relationships.

Vasuki Garg, Osman Y. Özaltın, Maria E. Mayorga, and Sherrie Bosisto. 2025. Detecting Illicit Massage Businesses by Leveraging Graph Machine Learning. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 9647–9655. https://doi.org/10.24963/ijcai.2025/1072
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards