RESUMO
The illegal wildlife trade (IWT) threatens conservation and biosecurity efforts. The Internet has greatly facilitated the trade of wildlife, and researchers have increasingly examined the Internet to uncover illegal trade. However, most efforts to locate illegal trade on the Internet are targeted to one or few taxa or products. Large-scale efforts to find illegal wildlife on the Internet (e-commerce, social media, dark web) may be facilitated by a systematic compilation of illegally traded wildlife taxa and their uses. Here, we provide such a dataset. We used seizure records from three global wildlife trade databases to compile the identity of seized taxa along with their intended usage (i.e., use-type). Our dataset includes c. 4.9k distinct taxa representing c. 3.3k species and contains c. 11k taxa-use combinations from 110 unique use-types. Further, we acquired over 45k common names for seized taxa from over 100 languages. Our dataset can be used to conduct large-scale broad searches of the Internet to find illegally traded wildlife. Further, our dataset can be filtered for more targeted searches of specific taxa or derived products.
RESUMO
Automated monitoring of websites that trade wildlife is increasingly necessary to inform conservation and biosecurity efforts. However, e-commerce and wildlife trading websites can contain a vast number of advertisements, an unknown proportion of which may be irrelevant to researchers and practitioners. Given that many wildlife-trade advertisements have an unstructured text format, automated identification of relevant listings has not traditionally been possible, nor attempted. Other scientific disciplines have solved similar problems using machine learning and natural language processing models, such as text classifiers. Here, we test the ability of a suite of text classifiers to extract relevant advertisements from wildlife trade occurring on the Internet. We collected data from an Australian classifieds website where people can post advertisements of their pet birds (n = 16.5k advertisements). We found that text classifiers can predict, with a high degree of accuracy, which listings are relevant (ROC AUC ≥ 0.98, F1 score ≥ 0.77). Furthermore, in an attempt to answer the question 'how much data is required to have an adequately performing model?', we conducted a sensitivity analysis by simulating decreases in sample sizes to measure the subsequent change in model performance. From our sensitivity analysis, we found that text classifiers required a minimum sample size of 33% (c. 5.5k listings) to accurately identify relevant listings (for our dataset), providing a reference point for future applications of this sort. Our results suggest that text classification is a viable tool that can be applied to the online trade of wildlife to reduce time dedicated to data cleaning. However, the success of text classifiers will vary depending on the advertisements and websites, and will therefore be context dependent. Further work to integrate other machine learning tools, such as image classification, may provide better predictive abilities in the context of streamlining data processing for wildlife trade related online data.
