Developing Typologies of Online (Potentially) Illegal Wildlife Product Sellers

• In Event: Poster Session 1

Abstract

After COVID-19, there has been a major shift of illegal wildlife trade (IWT) from physical stores to online marketplaces, leading to a variety of challenges for e-commerce regulators and law enforcement. The growing traffic of online sales brings with it a major challenge to identify and understand the characteristics of the sellers selling these products. We developed data extraction and analysis models created using machine learning (ML) and large language models (LLMs) to extract data on potential illegal sales on online marketplaces. Information, including product details (title, type, description, and price) and seller details (seller ID, variety of products, frequency of sales, modes, and duration of operations) pertaining to small-leather products, has been used to examine the a) landscape of sellers; b) the products sold; and c) cross-platform engagement with the aim to develop a framework for online seller typologies. The proposed framework can inform targeted and effective responses to IWT carried out on online marketplaces.

Authors

• Ulhas Gondhali, John Jay College of Criminal Justice

• Gohar A. Petrossian, John Jay College of Criminal Justice

• Juliana Barbosa, New York University

• Juliana Freire, New York University

• Sunandan Chakraborty, Indiana University

• Jennifer Jacquet, University of Miami

• Kinshuk Sharma, Indiana University