Scientists at the University of Helsinki are developing artificial intelligence-based tactics to help detect traces of the illegal wildlife trade on social media.
The tactics, described in the latest issue of the journal Conservation Biology, use machine learning methods and natural language processing to mine social media platforms for evidence of illegal animal trafficking. This AI-supported approach can quickly sift through thousands of images and textual data and flag posts that appear to contain evidence of illegal activity. Once posts have been identified, metadata can provide clues about the origin of the post as well as possible collaborators. This information can then be passed on to law enforcement to pursue.
“Machine learning algorithms can be trained to detect which species or wildlife products, such as rhino horns, appear in an image or video contained in social media posts, while also classifying their setting, such as a natural habitat or a marketplace.”
— Christoph Fink, Information Scientist, University of Helsinki
Historically, analyzing social media for evidence of illegal wildlife trading required specially trained humans and a prohibitively large amount of time. However, recent advances in machine learning have enabled computers to accurately identify a variety of species nearly instantaneously.
The scientists responsible for the development of these AI-based detection tools hope they will be used to reduce the number of instances of illegal trafficking and to advance wildlife conservation efforts.