Skip to main content
Vai all'homepage della Commissione europea (si apre in una nuova finestra)
italiano italiano
CORDIS - Risultati della ricerca dell’UE
CORDIS

Quantifying the global patterns and trends of the illegal wildlife trade: from artificial intelligence to financial market analysis

Periodic Reporting for period 4 - WILDTRADE (Quantifying the global patterns and trends of the illegal wildlife trade: from artificial intelligence to financial market analysis)

Periodo di rendicontazione: 2023-12-01 al 2024-05-31

The illegal wildlife trade in one of the major threats affecting the global biodiversity crisis. Wildlife trade is also linked to the spreading of zoonotic diseases, such as coronavirus disease 2019. International and European policies call for actions to halt illegal wildlife trade. In the Digital Age, an important part of the wildlife trade has moved to online platforms, especially social media platforms. The WILDTRADE project used machine learning methods and novel data sources mined from social media and other digital platforms, in combination with newly collected economic data, to quantify global patterns and trends of the illegal wildlife trade and how market forces shape them. Worldwide, we found evidence of online trade spread across multiple digital platforms and involving multiple species, including threatened species that are at highest risk of extinction. We also found that online wildlife trade can be context dependent, varying across regions and in terms of the species that are involved. Species rarity and market scarcity can enhance demand for these species and products. Feelings of care, such as attachment, affection, nurture, which we found to be dominant motivations for exotic pet keepers, could be used to help support conservation of the species in the wild. The methods developed as part of this project can be used to cost-effectively monitor and help stop the illegal wildlife trade on online platforms. Our results also support moving toward empowering local communities with stronger property rights over wildlife and delivering more benefits to them as important measures to help prevent the illegal supply of species and thereof products to online and other markets.
We have developed novel application methods to automatically collect and analyze textual, visual, and audio content from multiple digital platforms. An end-to-end pipeline starts from searching and downloading information about species threatened by wildlife trade and proceeds with implementing natural language processing and machine learning methods to filter and retain only relevant information for further analyses. A ‘Named Entity Recognition model’ extracts additional relevant information. This information includes reported prices and quantities of traded animals. The data collection framework follows data privacy and protection safeguards to comply with the European Union's General Data Protection Regulation. The resulting database was used to identify which species and thereof products are traded online globally.

Worldwide, there is evidence of online trade on multiple digital platforms involving multiple species across the Tree of Life. The online wildlife trade also involves species that are at highest risk of extinction. When investigating the magnitude and geographic distribution of global online trade of endemic and range-restricted reptile species from the Lesser Antilles, for example, online trade involved threatened species according to the International Union for the Conservation of Nature Red List and species listed in the Convention on International Trade in Endangered Species of Wild Fauna and Flora (CITES) Appendices. Germany was the country with the highest number of advertisements, followed by the United States, the Netherlands and United Kingdom. Based on data from sale advertisements that included price and currency data, prices ranged from one to over a thousand Euros. Our results also highlight that the dynamics of the online wildlife trade are context dependent. For example, we have examined the spatial characteristics of the songbird trade in Indonesia, using multiple online data sources, including citizen science data, small advertisements from online marketplace platforms, and videos. Data from these digital sources gave rich insights into the spatial, temporal and taxonomic structure of online wildlife trade. We also found that the asking prices on online marketplaces were significantly higher than the prices stated in an independently carried out consumer survey. We also analyzed trade across five digital platforms and species of conservation concern from a global biodiversity hotspot, the Philippines. We identified trade posts focusing on 108 species, 79 of which were classified as threatened. We observed an important proportion of plant-related trade hits. Trade mainly occurred on webpages indexed in Google and on Twitter.

We also conducted online surveys and choice experiments to explore how consumers' perceptions of rarity influence their preferences for exotic pets. Our findings indicate that species at risk of extinction, in limited supply, sourced from the wild, or subject to trade restrictions were the least preferred by respondents. Pet keepers were primarily motivated by feelings of care—such as attachment, affection, and nurture—along with curiosity and passion for the species. Additionally, respondents expressed a willingness to support the conservation of species in the wild. These results emphasize that relational dimensions are crucial factors in the decision to own exotic pets. We also developed a novel framework to summarize and gain insights into the demand for rarity and scarcity in the wildlife trade. Specifically, we examined the interplay between species rarity and market scarcity, their independent and combined effects on consumer preferences for wildlife, and the potential conservation implications.

Moreover, we suggested that the illegal trade in wildlife products, such as elephant ivory and rhino horn, is driven by persistent consumer demand and market speculation, facilitated by weak governance, inadequate species protection resources, and the alienation of local communities who bear the costs of coexisting with these species. Strategies that empower local communities with stronger property rights over wildlife and provide them with more benefits are underutilized in the current efforts to combat the international illegal wildlife trade.
The WILDTRADE project has successfully developed tools for efficiently monitoring the illegal wildlife trade on online platforms and assessed how market forces shape the trade. Our application of machine learning methods for automated content identification of the online wildlife trade are especially innovative and have allowed creating of a novel database of online wildlife trade in species and thereof products. We have identified areas of high pressure from illegal wildlife trade and examined the patterns of supply and demand of species threatened by illegal wildlife trade. We have investigated what are the implications for conservation of the interplay between species rarity and market scarcity, their independent and combined effects on consumer preferences for wildlife. We have also found out that feelings of care—such as attachment, affection, and nurture— among exotic pet owners can be used to help support the conservation of species in the wild.
Number of Lesser Antillean reptile advertisements per country.
The supply chain of Indonesia’s online songbird trade and its spaces and network.
Feature visualisation for online wildlife trade images with highest output activation.
Example of four types of Named Entities extracted along with the sentence they appear in
Il mio fascicolo 0 0