Using artificial intelligence to investigate illegal wildlife trade on social media

March 12, 2018, University of Helsinki
Dr. Enrico Di Minin has been working and collaborating with conservation authorities in South Africa for the last 10 years. Credit: Enrico Di Minin

Illegal wildlife trade is one of the biggest threats to biodiversity conservation and is currently expanding to social media. This is a worrisome trend, given the ease of access and popularity of social media. Efficient monitoring of illegal wildlife trade on social media is therefore crucial for conserving biodiversity.

In a new article published in the journal Conservation Biology, scientists from the University of Helsinki, Digital Geography Lab, argue that methods from can be used to help monitor the on .

Tools for conserving biodiversity

Dr. Enrico Di Minin, a conservation scientist at the University of Helsinki, who leads an interdisciplinary research group where methods from artificial intelligence are being developed and used to investigate the supply chain of the illegal wildlife trade in an innovative and novel way, stresses the importance of such novel methods to identify relevant data on the illegal wildlife trade from social platforms.

"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," says Dr. Di Minin

"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. Despite their potential, approaches from artificial intelligence are still rarely used in addressing the biodiversity crisis", he says.

Southern white rhinoceros (Ceratotherium simum simum) in an undisclosed protected area in South Africa. Credit: Enrico Di Minin

Images, metadata and meaning of a sentences

Many provide an application programming interface that allows researchers to access user-generated text, images and videos, as well as the accompanying metadata, such as where and when the content was uploaded, and connections between the users.

MSc Christoph Fink stresses how machine learning methods provide an efficient means of monitoring illegal wildlife trade on social media.

"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," Fink says.

Assistant professor Tuomo Hiippala highlights how machine learning methods can be used to process the language of .

"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. Most importantly, machine learning algorithms can process combinations of verbal, visual and audio-visual content", Hiippala says.

In the ongoing project, the researchers are applying machine learning methods to automatically identify content pertaining to illegal wildlife trade on social media. They also stress the importance of collaborating with and social media companies to further improve the outcomes of their work and help stop illegal wildlife trade on social media.

Explore further: Trade in rare plants on social media must be monitored

More information: Enrico Di Minin et al, Use of machine learning to investigate illegal wildlife trade on social media, Conservation Biology (2018). DOI: 10.1111/cobi.13104

Related Stories

Trade in rare plants on social media must be monitored

March 15, 2016

A study conducted by the University of Kent's Dr Amy Hinsley and Dr David Roberts, and published by Conservation Biology, represents the first large-scale global survey of wildlife trade via a social-media site, using the ...

Using science to combat illegal wildlife trade

July 28, 2017

Leading scientists from around the world convened this week at the International Congress for Conservation Biology in Cartagena, Colombia, to discuss how to better leverage science to combat illegal wildlife trade—both ...

A bird in the bush equals money in the hand

March 1, 2018

A new study by the Wildlife Conservation Society (WCS) and Foundations of Success (FOS) finds that an ecotourism strategy based on "direct payments," where local people are compensated for the amount of wildlife seen by tourists, ...

Recommended for you

What's behind the color and pattern of bird feathers?

September 26, 2018

While it may be true, as the old adage goes, that 'birds of a feather flock together,' what is less certain is how the feathers on those birds come to have their distinct patterns and colorations. Current data suggest that ...

A mechanism of color pattern formation in ladybird beetles

September 26, 2018

Many ladybirds have attractive color patterns consisting of black and red. This prominent color pattern is thought to function as a warning that indicates to predators that they are very bitter and unpalatable. A research ...

Zika and yellow fever—vaccines without eggs

September 26, 2018

A team led by researchers from the Max Planck Institute for Dynamics of Complex Technical Systems in Magdeburg is developing methods with which viruses for vaccines can be replicated in significantly higher concentrations ...

Microbial dark matter dominates Earth's environments

September 26, 2018

Uncultured microbes—those whose characteristics have never been described because they have not yet been grown in a lab culture—could be dominating nearly all the environments on Earth except for the human body, according ...

How leaves talk to roots

September 26, 2018

New findings show that a micro RNA from the shoot keeps legume roots susceptible to symbiotic infection by downregulating a gene that would otherwise hinder root responses to symbiotic bacteria. These findings reveal what ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.