March 12 (UPI) -- Illegal wildlife trade and related activities are increasingly being coordinated via social media, new research suggests. In order to track the illicit trade, scientists have designed and deployed new machine-learning algorithms.
"Currently, the lack of tools for efficient monitoring of high-volume social media data limits the capability of law enforcement agencies to curb illegal wildlife trade," Enrico Di Minin, a conservation scientist at the University of Helsinki in Finland, said in a news release. "Processing such data manually is inefficient and time consuming, but methods from artificial intelligence, such as machine-learning algorithms, can be used to automatically identify relevant information."
Machine learning has been used to address a wide variety of problems, but this is one of the first times the technology has been used to confront threats to biodiversity.
Researchers designed the new algorithms to identify specific items, like rhino horns, among streams of social media content. The machine-learning technology can also identify information related the target item, such as the habitat in which poachers are pictured posing with a dead animal or the marketplace where an illegal product is advertised for sale.
Scientists say their algorithms can be trained to analyze both images and language.
"Natural language processing can be used to infer the meaning of a sentence and to classify the sentiment of social media users towards illegal wildlife trade," said assistant professor Tuomo Hiippala. "Most importantly, machine learning algorithms can process combinations of verbal, visual and audio-visual content."
As researchers continue to improve their algorithms, they hope to partner with social media companies and local law enforcement agencies to better coordinate efforts to snuff out the illegal wildlife trade.
Scientists detailed their technological approach to conservation in the journal Conservation Biology.