Since COVID-19, the illegal wildlife trade (IWT) has made a massive transition from physical to online marketplaces, creating new challenges for identifying and tracking the trade of reptile leather products. Social network analysis has been used in the past to identify networks of key actors and generate strategies to dismantle these networks. However, these analyses have been limited to actors interacting in the physical space. We utilise machine learning (ML) and large language models (LLMs) to extract advertisements on potential illegal sales of small leather items on eBay as the case-study marketplace. We use social network analysis to identify key actors, products, and eBay sites where these activities occur, and network percolation analysis to determine which network disruption strategies offer the most optimal network dismantlement. We found that online reptile leather trade is highly concentrated, with a small number of species, product types, and countries dominating the market, especially for such luxury products as crocodile bags. Network percolation analyses revealed that targeted interventions focusing on high-degree product types (rather than sellers or shipping countries) are most effective at disrupting the market. These findings suggest that regulatory agencies should prioritise enforcement at key market chokepoints by requiring all online listings of reptile leather products to display valid CITES permits, include the full scientific and common species names, and show non-reusable CITES tags in product images. E-commerce platforms like eBay must enforce these requirements to ensure compliance with domestic and international wildlife trade laws.
扫码关注我们
求助内容:
应助结果提醒方式:
