A framework for investigating illegal wildlife trade on social media with machine learning

Potential for Artificial Intelligence (AI) and Machine Learning (ML) Applications in Biodiversity Conservation, Managing Forests, and Related Services in India

The recent advancement in data science coupled with the revolution in digital and satellite technology has improved the potential for artificial intelligence (AI) applications in the forestry and wildlife sectors. India shares 7% of global forest cover and is the 8th most biodiverse region in the world. However, rapid expansion of developmental projects, agriculture, and urban areas threaten the country’s rich biodiversity. Therefore, the adoption of new technologies like AI in Indian forests and biodiversity sectors can help in effective monitoring, management, and conservation of biodiversity and forest resources. We conducted a systematic search of literature related to the application of artificial intelligence (AI) and machine learning algorithms (ML) in the forestry sector and biodiversity conservation across globe and in India (using ISI Web of Science and Google Scholar). Additionally, we also collected data on AI-based startups and non-profits in forest and wildlife sectors to understand the growth and adoption of AI technology in biodiversity conservation, forest management, and related services. Here, we first provide a global overview of AI research and application in forestry and biodiversity conservation. Next, we discuss adoption challenges of AI technologies in the Indian forestry and biodiversity sectors. Overall, we find that adoption of AI technology in Indian forestry and biodiversity sectors has been slow compared to developed, and to other developing countries. However, improving access to big data related to forest and biodiversity, cloud computing, and digital and satellite technology can help improve adoption of AI technology in India. We hope that this synthesis will motivate forest officials, scientists, and conservationists in India to explore AI technology for biodiversity conservation and forest management.

Concerned or Apathetic? Using Social Media Platform (Twitter) to Gauge the Public Awareness about Wildlife Conservation: A Case Study of the Illegal Rhino Trade

The illegal wildlife trade is resulting in worldwide biodiversity loss and species’ extinction. It should be exposed so that the problems of conservation caused by it can be highlighted and resolutions can be found. Social media is an effective method of information dissemination, providing a real-time, low-cost, and convenient platform for the public to release opinions on wildlife protection. This paper aims to explore the usage of social media in understanding public opinions toward conservation events, and illegal rhino trade is an example. This paper provides a framework for analyzing rhino protection issues by using Twitter. A total of 83,479 useful tweets and 33,336 pieces of users’ information were finally restored in our database after filtering out irrelevant tweets. With 2422 records of trade cases, this study builds up a rhino trade network based on social media data. The research shows important findings: (1) Tweeting behaviors are somewhat affected by the information of traditional mass media. (2) In general, countries and regions with strong negative sentiment tend to have high volume of rhino trade cases, but not all. (3) Social celebrities’ participation in activities arouses wide public concern, but the influence does not last for more than a month. NGOs, GOs, media, and individual enterprises are dominant in the dissemination of information about rhino trade. This study contributes in the following ways: First, this paper conducts research on public opinions toward wildlife conservation using natural language processing technique. Second, this paper offers advice to governments and conservationist organizations, helping them utilize social media for protecting wildlife.

Identifying opportunities for expert-mediated triangulation in monitoring wildlife trade on social media

Wildlife trade has rapidly expanded on social media platforms in recent years, offering an easy means for traders to access international markets. Investigating this trade activity poses a complex challenge to researchers seeking to understand online trade and moderators seeking to disrupt illicit and harmful activity. Current survey methods frequently rely on text-based searches and focus on posts in which the advertisement is explicit. However, such approaches risk overlooking a growing volume of relevant content, particularly outside social media groups. We used posts from pages promoting West African birds for trade as a case study to explore the availability of information for making inferences about trade activity on social media, specifically information indicating that trade activity was occurring or that could be used to infer trade routes. We recorded 400 posts from 12 pages that we inferred either promoted or facilitated wildlife trade, of which 19.7% were explicit advertisements and 23.8% contained taxa-related terms. In the remaining 341 posts, profile information was the most common indicator of trade activity, but a variety of indicators (e.g., images of birds in trade and trade enquiries) were identified across imagery, text, and comments. We identified multiple types of geographical information that could help infer trade routes and thus the likely legality of trade, although most were relatively rare and sometimes contradictory. Our findings suggest that triangulating multiple types of information from within, across, and beyond posts is vital for effectively identifying and interpreting wildlife trade content on social media. Therefore, were commend that expert-mediated triangulation should be integrated in and used alongside automated detection systems and moderating practices of social media companies.

Evaluating the benefits and risks of social media for wildlife conservation

Given its extensive volume and reach, social media has the potential to widely spread conservation messaging and be a powerful tool to mobilize social change for conserving biodiversity. We synthesized gray and primary academic literature to investigate the effects of social media on wildlife conservation, revealing several overarching benefits and risks. We found that social media can increase pro-conservation behaviours among the public, increase conservation funding, and incite policy changes. Conversely, social media can contribute to species exploitation and illegal trade, cause unprecedented increases in tourism in protected areas, and perpetuate anti-conservation behaviours via misinformation. In most cases, we found that content sharing on social media did not result in a detectable impact on conservation; in this paper, however, we focus on providing examples where conservation impact was achieved. We relate these positive and negative outcomes of social media to psychological phenomena that may influence conservation efforts and discuss limitations of our findings. We conclude with recommendations of best practices to social media administrators, public social media users, nongovernmental organizations, and governing agencies to minimize conservation risks while maximizing beneficial outcomes. By improving messaging, policing online misconduct, and providing guidance for action, social media can help achieve wildlife conservation goals.

Quantitative conservation geography

Ongoing biodiversity loss represents the erosion of intrinsic value of living nature, reduces the contributions nature provides to people, and undermines efforts to move towards sustainability. We propose the recognition of quantitative conservation geography as a subfield of conservation science that studies where, when, and what conservation actions could be implemented in order to mitigate threats and promote sustainable people-nature interactions. We outline relevant methods and data needed in quantitative conservation geography. We also discuss the importance of filling information gaps, for example by using emerging technologies and digital data sources, for the further advancement of this subfield. Quantitative conservation geography can help inform the implementation of national and international conservation actions and policy to help stem the global biodiversity crisis.

The Partnership of Citizen Science and Machine Learning: Benefits, Risks, and Future Challenges for Engagement, Data Collection, and Data Quality

Advances in artificial intelligence (AI) and the extension of citizen science to various scientific areas, as well as the generation of big citizen science data, are resulting in AI and citizen science being good partners, and their combination benefits both fields. The integration of AI and citizen science has mostly been used in biodiversity projects, with the primary focus on using citizen science data to train machine learning (ML) algorithms for automatic species identification. In this article, we will look at how ML techniques can be used in citizen science and how they can influence volunteer engagement, data collection, and data validation. We reviewed several use cases from various domains and categorized them according to the ML technique used and the impact of ML on citizen science in each project. Furthermore, the benefits and risks of integrating ML in citizen science are explored, and some recommendations are provided on how to enhance the benefits while mitigating the risks of this integration. Finally, because this integration is still in its early phases, we have proposed some potential ideas and challenges that can be implemented in the future to leverage the power of the combination of citizen science and AI, with the key emphasis being on citizen science in this article.

Text classification to streamline online wildlife trade analyses

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.

A Literature Synthesis of Actions to Tackle Illegal Parrot Trade

The order Psittaciformes is one of the most prevalent groups in the illegal wildlife trade. Efforts to understand this threat have focused on describing the elements of the trade itself: actors, extraction rates, and routes. However, the development of policy-oriented interventions also requires an understanding of how research aims and actions are distributed across the trade chain, regions, and species. We used an action-based approach to review documents published on illegal Psittaciformes trade at a global scale to analyze patterns in research aims and actions. Research increased exponentially in recent decades, recording 165 species from 46 genera, with an over representation of American and Australasian genera. Most of the research provided basic knowledge for the intermediary side of the trade chain. Aims such as the identification of network actors, zoonosis control, and aiding physical detection had numerous but scarcely cited documents (low growth rate), while behavior change had the highest growth rate. The Americas had the highest diversity of research aims, contributing with basic knowledge, implementation, and monitoring across the whole trade chain. Better understanding of the supply side dynamics in local markets, actor typology, and actor interactions are needed. Protecting areas, livelihood incentives, and legal substitutes are actions under-explored in parrots, while behavior change is emerging.

Exploring human-nature interactions in national parks with social media photographs and computer vision

Understanding the activities and preferences of visitors is crucial for managing protected areas and planning conservation strategies. Conservation culturomics promotes the use of user-generated online content in conservation science. Geotagged social media content is a unique source of in situ information on human presence and activities in nature. Photographs posted on social media platforms are a promising source of information, but analyzing large volumes of photographs manually remains laborious. We examined the application of state-of-the-art computer-vision methods to studying human-nature interactions. We used semantic clustering, scene classification, and object detection to automatically analyze photographs taken in Finnish national parks by domestic and international visitors. Our results showed that human-nature interactions can be extracted from user-generated photographs with computer vision. The different methods complemented each other by revealing broad visual themes related to level of the data set, landscape photogeneity, and human activities. Geotagged photographs revealed distinct regional profiles for national parks (e.g., preferences in landscapes and activities), which are potentially useful in park management. Photographic content differed between domestic and international visitors, which indicates differences in activities and preferences. Information extracted automatically from photographs can help identify preferences among diverse visitor groups, which can be used to create profiles of national parks for conservation marketing and to support conservation strategies that rely on public acceptance. The application of computer-vision methods to automatic content analysis of photographs should be explored further in conservation culturomics, particularly in combination with rich metadata available on social media platforms.

Digital data sources and methods for conservation culturomics

Ongoing loss of biological diversity is primarily the result of unsustainable human behavior. Thus, the long-term success of biodiversity conservation depends on a thorough understanding of human-nature interactions. Such interactions are ubiquitous but vary greatly in time and space and are difficult to monitor efficiently at large spatial scales. However, the Information Age also provides new opportunities to better understand human-nature interactions because many aspects of daily life are recorded in a variety of digital formats. The emerging field of conservation culturomics aims to take advantage of digital data sources and methods to study human-nature interactions and thus to provide new tools for studying conservation at relevant temporal and spatial scales. Nevertheless, technical challenges associated with the identification, access, and analysis of relevant data hamper the wider adoption of culturomics methods. To help overcome these barriers, we propose a conservation culturomics research framework that addresses data acquisition, analysis, and inherent biases. The main sources of culturomic data include web pages, social media, and other digital platforms from which metrics of content and engagement can be obtained. Obtaining raw data from these platforms is usually desirable but requires careful consideration of how to access, store, and prepare the data for analysis. Methods for data analysis include network approaches to explore connections between topics, time-series analysis for temporal data, and spatial modeling to highlight spatial patterns. Outstanding challenges associated with culturomics research include issues of interdisciplinarity, ethics, data biases, and validation. The practical guidance we offer will help conservation researchers and practitioners identify and obtain the necessary data and carry out appropriate analyses for their specific questions, thus facilitating the wider adoption of culturomics approaches for conservation applications.

Combining culturomic sources to uncover trends in popularity and seasonal interest in plants

Culturomic tools enable the exploration of trends in human-nature interactions, although they entail inherent biases and necessitate careful validation. Furthermore, people may engage with nature across different culturomic data sets differently. We evaluated people's digital interest and engagement with plant species based on Wikipedia and Google data and explored the conservation implications of these temporal interest patterns. As a case study, we explored the digital footprints of the most popular plant species in Israel. We analyzed 4 years of daily page views from Hebrew Wikipedia and 10 years of daily Google search volume in Israel. We modeled popularity of plant species in these 2 data sets based on a suite of plant attributes. We further explored the seasonal trends of people's interest in each species. We found differences in how people interacted digitally with plants in Wikipedia and Google. Overall, in Google, searches for species that have utility to humans were more common, whereas in Wikipedia, plants that serve as cultural emblems received more attention. Furthermore, in Google, popular species attracted more attention over time, opposite to the trend in Wikipedia. In Google, interest in species with short bloom duration exhibited more pronounced seasonal patterns, whereas in Wikipedia, seasonality of interest increased as bloom duration increased. Together, our results suggest that people's digital interactions with nature may be inherently different depending on the sources explored, which may affect use of this information for conservation. Although culturomics holds much promise, better understanding of its underpinnings is important when translating insights into conservation actions.

How to address data privacy concerns when using social media data in conservation science

Social media data are being increasingly used in conservation science to study human-nature interactions. User-generated content, such as images, video, text, and audio, and the associated metadata can be used to assess such interactions. A number of social media platforms provide free access to user-generated social media content. However, similar to any research involving people, scientific investigations based on social media data require compliance with highest standards of data privacy and data protection, even when data are publicly available. Should social media data be misused, the risks to individual users' privacy and well-being can be substantial. We investigated the legal basis for using social media data while ensuring data subjects' rights through a case study based on the European Union's General Data Protection Regulation. The risks associated with using social media data in research include accidental and purposeful misidentification that has the potential to cause psychological or physical harm to an identified person. To collect, store, protect, share, and manage social media data in a way that prevents potential risks to users involved, one should minimize data, anonymize data, and follow strict data management procedure. Risk-based approaches, such as a data privacy impact assessment, can be used to identify and minimize privacy risks to social media users, to demonstrate accountability and to comply with data protection legislation. We recommend that conservation scientists carefully consider our recommendations in devising their research objectives so as to facilitate responsible use of social media data in conservation science research, for example, in conservation culturomics and investigations of illegal wildlife trade online.

Focus and social contagion of environmental organization advocacy on Twitter

Agriculture, overexploitation, and urbanization remain the major threats to biodiversity in the Anthropocene. The attention these threats garner among leading environmental nongovernmental organizations (eNGOs) and the wider public is critical in fostering the political will necessary to reverse biodiversity declines worldwide. I analyzed the advocacy of leading eNGOs on Twitter by scraping account timelines, screening content for advocacy relating to biodiversity threats and, for prevalent threats, further screening content for positive and negative emotional language with a sentiment lexicon. Twitter advocacy was dominated by the major threats of climate change and overexploitation and the minor threat of plastic pollution. The major threats of agriculture, urbanization, invasions, and pollution were rarely addressed. Content relating to overexploitation and plastic pollution was more socially contagious than other content. Increasing emotional negativity further increased social contagion, whereas increasing emotional positivity did not. Scientists, policy makers, and eNGOs should consider how narrowly focused advocacy on platforms like Twitter will contribute to effective global biodiversity conservation.

Online media reveals a global problem of discarded containers as deadly traps for animals

The widespread occurrence of litter is a severe threat to global ecosystems. We have analyzed online media, to assess the diversity of animals that are prone to getting trapped in discarded containers and check which kind of containers is the most common trap for animals. A total of 503 records from around the world (51 countries, 6 continents) have been found. These include invertebrates (17 taxa, ca.1050 dead individuals), and vertebrates (98 taxa, 496 individuals including 44 carcasses). The latter group was most frequently represented by mammals (78.5% of all cases), then reptiles (15.3%), birds (1.2%), fish (1.0%) and amphibians (0.4%). Nearly 12.5% of the determined vertebrates are classified as vulnerable, endangered or critically endangered, according to the IUCN. Although most trapped individuals were smaller animals, bigger ones such as monitor lizards (Varanus spp.) or large carnivores were also recorded. In most cases, animals were trapped in glass or plastic jars (32.4%), drink cans (16.5%), and steel cans (16.3%). Our results demonstrate that discarded containers can be a threat to all major groups of animals. In order to address this phenomenon, it is necessary to decrease a global production of debris, implement container deposit legislation and organize repeatable cleanup actions.

The "Bio-Crime Model" of Cross-Border Cooperation Among Veterinary Public Health, Justice, Law Enforcements, and Customs to Tackle the Illegal Animal Trade/Bio-Terrorism and to Prevent the Spread of Zoonotic Diseases Among Human Population

Illegal animal trade (pet, wildlife, animal products, etc.) is an example of transnational organized crime (T.O.C.) that generates a large business with huge profit margins. This criminal activity causes several negative effects on human health (zoonoses), animal health and welfare, market protection, consumer fraud and may be used as tool of agro/bio-terrorism. Illegal animal trade can facilitate the spread of zoonoses that are defined as diseases and infections that are transmitted by vertebrate animals to man. Humans are affected by more than 1,700 known pathogens: 60% of existing human infectious diseases are zoonotic and at least 75% of emerging infectious diseases of humans have an animal origin and 72% of zoonoses originate from wildlife or exotic animals. The Bio-Crime Project was developed in 2017 by Friuli Venezia Giulia Region (Italy) and Land Carinthia (Austria) together with other public institutions to combat illegal animal trade and to reduce the risk of disease transmission from animals to humans. Project partners agreed that a multi-agency approach was required to tackle the illegal animal trade that was high value, easy to undertake and transnational crime. The Bio-crime model of cross-border cooperation introduces the novel approach of replicating the cooperative framework given by the triad of Veterinary Public Health, Justice and Law Enforcements/Customs across borders using the International Police and Custom Cooperation Centres (IPCCCs) as a connection link among public entities of the neighbor countries. This model has been recognized as a best practice at European level because it can be easily replicated and scaled up without any supplementary cost for Member States.

Artificial Intelligence Meets Citizen Science to Supercharge Ecological Monitoring

The development and uptake of citizen science and artificial intelligence (AI) techniques for ecological monitoring is increasing rapidly. Citizen science and AI allow scientists to create and process larger volumes of data than possible with conventional methods. However, managers of large ecological monitoring projects have little guidance on whether citizen science, AI, or both, best suit their resource capacity and objectives. To highlight the benefits of integrating the two techniques and guide future implementation by managers, we explore the opportunities, challenges, and complementarities of using citizen science and AI for ecological monitoring. We identify project attributes to consider when implementing these techniques and suggest that financial resources, engagement, participant training, technical expertise, and subject charisma and identification are important project considerations. Ultimately, we highlight that integration can supercharge outcomes for ecological monitoring, enhancing cost-efficiency, accuracy, and multi-sector engagement.

Citizen science and artificial intelligence (AI) are often used in isolation for ecological monitoring, but their integration likely has emergent benefits for management and scientific inquiry. We explore the complementarity of citizen science and AI for ecological monitoring, highlighting key opportunities and challenges. We show that strategic integration of citizen science and AI can improve outcomes for conservation activities. For example, coupling the public engagement benefits of citizen science with the advanced analytical capabilities of AI can increase multi-stakeholder accord on issues of public and scientific interest. Furthermore, both techniques speed up data collection and processing compared with conventional scientific techniques, suggesting that their integration can fast-track monitoring and conservation actions. We present key project attributes that will assist project managers in prioritizing the resources needed to implement citizen science, AI, or preferably both.

Deep learning for environmental conservation

The last decade has transformed the field of artificial intelligence, with deep learning at the forefront of this development. With its ability to 'self-learn' discriminative patterns directly from data, deep learning is a promising computational approach for automating the classification of visual, spatial and acoustic information in the context of environmental conservation. Here, we first highlight the current and future applications of supervised deep learning in environmental conservation. Next, we describe a number of technical and implementation-related challenges that can potentially impede the real-world adoption of this technology in conservation programmes. Lastly, to mitigate these pitfalls, we discuss priorities for guiding future research and hope that these recommendations will help make this technology more accessible to environmental scientists and conservation practitioners.

Analyzing the popularity of YouTube videos that violate mountain gorilla tourism regulations

Although ecotourism is expected to be compatible with conservation, it often imposes negative effects on wildlife. The ecotourism of endangered mountain gorillas has attracted many tourists and functioned as a key component of their conservation. There might be expectations on the part of tourists to observe or interact with gorillas in close proximity and such expectations may have been engendered by the contents of social media in this Information Age. However, the risk of disease transmission between humans and gorillas is a large concern and it is important to maintain a certain distance while observing gorillas to minimize risk. We conducted a content analysis and described the general characteristics of 282 YouTube videos related to mountain gorilla tourism. Humans and gorillas were observed simultaneously in 70% of the videos, and physical contact or close proximity within arm's reach were identified in 40%. To explore the factors affecting the number of views and likes that these videos received, we ran generalized linear mixed models and performed AIC model selection with 206 videos in which humans and gorillas were observed simultaneously. Videos obtained more views and likes when the thumbnail photos included humans and gorillas together, while videos with thumbnail photos of only gorillas did not obtain more views and likes compared with those that included no gorillas. Moreover, videos obtained more views and likes in cases where physical contact or close proximity within arm's reach with gorillas were clearly observed, compared with those that did not clearly include close human-gorilla interaction. These results suggest that human-gorilla interaction and proximity with gorillas attract more public attention than gorillas shown by themselves. Our study highlights the importance of further investigation on the direct link between such contents that violate tourism regulations and the conflicting situation.

Global wildlife trade across the tree of life

Wildlife trade is a multibillion dollar industry that is driving species toward extinction. Of >31,500 terrestrial bird, mammal, amphibian, and squamate reptile species, ~18% (N = 5579) are traded globally. Trade is strongly phylogenetically conserved, and the hotspots of this trade are concentrated in the biologically diverse tropics. Using different assessment approaches, we predict that, owing to their phylogenetic replacement and trait similarity to currently traded species, future trade will affect up to 3196 additional species-totaling 8775 species at risk of extinction from trade. Our assessment underscores the need for a strategic plan to combat trade with policies that are proactive rather than reactive, which is especially important because species can quickly transition from being safe to being endangered as humans continue to harvest and trade across the tree of life.

iEcology: Harnessing Large Online Resources to Generate Ecological Insights

Digital data are accumulating at unprecedented rates. These contain a lot of information about the natural world, some of which can be used to answer key ecological questions. Here, we introduce iEcology (i.e., internet ecology), an emerging research approach that uses diverse online data sources and methods to generate insights about species distribution over space and time, interactions and dynamics of organisms and their environment, and anthropogenic impacts. We review iEcology data sources and methods, and provide examples of potential research applications. We also outline approaches to reduce potential biases and improve reliability and applicability. As technologies and expertise improve, and costs diminish, iEcology will become an increasingly important means to gain novel insights into the natural world.

Assessing global popularity and threats to Important Bird and Biodiversity Areas using social media data

Understanding worldwide patterns of human use of sites of international significance for biodiversity conservation is crucial for meeting global conservation targets. However, robust global datasets are scarce. In this study, we used social media data, mined from Flickr and Twitter, geolocated in Important Bird and Biodiversity Areas (IBAs) to assess i) patterns of popularity; ii) relationships of this popularity with geographical and biological variables; and iii) identify sites under high pressure from visitors. IBAs located in Europe and Asia, and in temperate biomes, had the highest density of users. Sites of importance for congregatory species, which were also more accessible, more densely populated and provided more tourism facilities, received higher visitation than did sites richer in bird species. We found 17% of all IBAs assessed to be under very high threat also received high visitation. Our results show in which IBAs enhanced monitoring should be implemented to reduce potential visitation risks to sites of conservation concern for birds, and to harness the potential benefits of tourism for conservation.

Use of Machine Learning to Detect Wildlife Product Promotion and Sales on Twitter

Social media is an important channel for communication, information dissemination, and social interaction, but also provides opportunities to illicitly sell goods online, including the trade of wildlife products. In this study, we use the Twitter public application programming interface (API) to access Twitter messages in order to detect and classify suspicious wildlife trafficking and sale using an unsupervised machine learning topic model combined with keyword filtering and manual annotation. We choose two prohibited wildlife animals and related products: elephant ivory and pangolin, and collected tweets containing keywords and known code words related to these species. In total, we collected 138,357 tweets filtered for these keywords over a 14-day period and were able to identify 53 tweets from 38 unique users that we suspect promoted the sale of Ivory products, though no pangolin related promoted post were detected in this study. Study results show that machine learning combined with supplement analysis approaches such as those utilized in this study have the potential to detect illegal content without the use of an existing training data set. If developed further, these approaches can help technology companies, conservation groups, and law enforcement officials to expedite the process of identifying illegal online sales and stem supply for the billion-dollar criminal industry of online wildlife trafficking.

Popularity of pet otters on YouTube: evidence of an emerging trade threat

In response to growing reports of otters in the pet trade, and suggestions that the popularity of pet otters on social media may be driving demand, we collated YouTube videos of pet otters to test for trends in the number of videos published, their exposure (number of views) and popularity. We used English-language search terms to provide a global overview, as well as local language search terms for four South East Asian countries identified as being of potential importance in the pet otter trade (Indonesia, Malaysia, Thailand and Vietnam), and Japan. We found that not only had the number of videos depicting pet otters increased in the last two to three years (2016–2018), but that their popularity and/or engagement had also increased. Notwithstanding some country-level differences in the details of effects observed, the greatest increases in both the number of videos produced and their popularity occurred in Indonesia and Japan. At a global-level, commercial “viral” video sites appeared to be influential in terms of posting highly popular pet otter videos. At a national level, potentially influential videos tended to be produced by four or five individual otter owners. The appearance of phrases such as “I want one” in the comments section of the English-language videos, although not necessarily a statement of actual intent, suggests that these videos may be driving demand amongst their viewers and followers; similar analyses of video comments in each local language are warranted. Our results show an increase in social media activity that may not only be driving the apparent increase in popularity, but also amplifying awareness of the availability of these animals as pets, as well as creating and perpetuating the (erroneous) perception of otters as a suitable companion animal. At a global level, there are welfare concerns associated with otters in the pet trade, and, in South East Asia specifically, there are serious conservation concerns. We recommend increased regulation of these activities on social media, increased public awareness of the negative impacts of the pet trade on otters, and increased international protection. Specifically, we suggest the need to uplist both small-clawed and smooth-coated otters (Aonyxcinereus and Lutrogaleperspicillata, respectively) to CITES Appendix 1.