Identifying opportunities for expert-mediated triangulation in monitoring wildlife trade on social media

Wildlife trade has rapidly expanded on social media platforms in recent years, offering an easy means for traders to access international markets. Investigating this trade activity poses a complex challenge to researchers seeking to understand online trade and moderators seeking to disrupt illicit and harmful activity. Current survey methods frequently rely on text-based searches and focus on posts in which the advertisement is explicit. However, such approaches risk overlooking a growing volume of relevant content, particularly outside social media groups. We used posts from pages promoting West African birds for trade as a case study to explore the availability of information for making inferences about trade activity on social media, specifically information indicating that trade activity was occurring or that could be used to infer trade routes. We recorded 400 posts from 12 pages that we inferred either promoted or facilitated wildlife trade, of which 19.7% were explicit advertisements and 23.8% contained taxa-related terms. In the remaining 341 posts, profile information was the most common indicator of trade activity, but a variety of indicators (e.g., images of birds in trade and trade enquiries) were identified across imagery, text, and comments. We identified multiple types of geographical information that could help infer trade routes and thus the likely legality of trade, although most were relatively rare and sometimes contradictory. Our findings suggest that triangulating multiple types of information from within, across, and beyond posts is vital for effectively identifying and interpreting wildlife trade content on social media. Therefore, were commend that expert-mediated triangulation should be integrated in and used alongside automated detection systems and moderating practices of social media companies.

Automated summary

Wildlife trade has expanded rapidly on social media, creating challenges for researchers and moderators. Current survey methods overlook relevant content, highlighting the need for triangulating multiple sources of information to effectively identify wildlife trade content.