Text classification to streamline online wildlife trade analyses

The Internet can be vast source of data for the wildlife trade. However, data collected from the Internet is often numerous and messy, making data cleaning a task the requires a lot time and effort. Here, we tested if text classification can be used to speed up the process of data cleaning in relation to online data collected on the wildlife trade. We found that text classification models can predict with great accuracy relaxant advertisements, including the taxonomy of relevant species, using the text found in online advertisements. We recommend using text classification as a method to make data cleaning more efficient. Future efforts should try to pair text classification with image classification for improved efficiency.

By Oliver C. Stringham, Stephanie Moncayo, Katherine G. W. Hill, Adam Toomes, Lewis Mitchell, Joshua V. Ross, Phillip Cassey in Research

July 9, 2021

Abstract

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.

Posted on:
July 9, 2021
Length:
2 minute read, 303 words
Categories:
Research
Tags:
internet natural language processing wildlife trade illegal wildlife trade
See Also:
Challenges and perspectives on tackling illegal or unsustainable wildlife trade
Scientists' warning to humanity on illegal or unsustainable wildlife trade
Drivers of the live pet trade: the role of species traits, socioeconomic attributes and regulatory systems