Text classification to streamline online wildlife trade analyses

• Published in: PloS one Vol. 16; no. 7; p. e0254007
• Main Authors: Stringham, Oliver C, Moncayo, Stephanie, Hill, Katherine G. W, Toomes, Adam, Mitchell, Lewis, Ross, Joshua V, Cassey, Phillip
• Format: Journal Article
• Language: English
• Published: San Francisco Public Library of Science 09.07.2021; Public Library of Science (PLoS)
• Subjects: Advertising; Biodiversity; Biology and Life Sciences; Biosecurity; Birds; Classification; Classifiers; Computer and Information Sciences; Conservation; Context; Data collection; Data processing; Datasets; Electronic commerce; Evaluation; Food; Funding; Image classification; Internet; Learning algorithms; Machine learning; Natural language processing; Poultry; Reptiles & amphibians; Sensitivity analysis; Social Sciences; Streamlining; Text categorization; Text processing; Unstructured data; Websites; Wild animal trade; Wildlife conservation; Wildlife trade; Australia

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 practition...