Dataset Information

Big Data, Natural Language Processing, and Deep Learning to Detect and Characterize Illicit COVID-19 Product Sales: Infoveillance Study on Twitter and Instagram.

ABSTRACT: BACKGROUND:The coronavirus disease (COVID-19) pandemic is perhaps the greatest global health challenge of the last century. Accompanying this pandemic is a parallel "infodemic," including the online marketing and sale of unapproved, illegal, and counterfeit COVID-19 health products including testing kits, treatments, and other questionable "cures." Enabling the proliferation of this content is the growing ubiquity of internet-based technologies, including popular social media platforms that now have billions of global users. OBJECTIVE:This study aims to collect, analyze, identify, and enable reporting of suspected fake, counterfeit, and unapproved COVID-19-related health care products from Twitter and Instagram. METHODS:This study is conducted in two phases beginning with the collection of COVID-19-related Twitter and Instagram posts using a combination of web scraping on Instagram and filtering the public streaming Twitter application programming interface for keywords associated with suspect marketing and sale of COVID-19 products. The second phase involved data analysis using natural language processing (NLP) and deep learning to identify potential sellers that were then manually annotated for characteristics of interest. We also visualized illegal selling posts on a customized data dashboard to enable public health intelligence. RESULTS:We collected a total of 6,029,323 tweets and 204,597 Instagram posts filtered for terms associated with suspect marketing and sale of COVID-19 health products from March to April for Twitter and February to May for Instagram. After applying our NLP and deep learning approaches, we identified 1271 tweets and 596 Instagram posts associated with questionable sales of COVID-19-related products. Generally, product introduction came in two waves, with the first consisting of questionable immunity-boosting treatments and a second involving suspect testing kits. We also detected a low volume of pharmaceuticals that have not been approved for COVID-19 treatment. Other major themes detected included products offered in different languages, various claims of product credibility, completely unsubstantiated products, unapproved testing modalities, and different payment and seller contact methods. CONCLUSIONS:Results from this study provide initial insight into one front of the "infodemic" fight against COVID-19 by characterizing what types of health products, selling claims, and types of sellers were active on two popular social media platforms at earlier stages of the pandemic. This cybercrime challenge is likely to continue as the pandemic progresses and more people seek access to COVID-19 testing and treatment. This data intelligence can help public health agencies, regulatory authorities, legitimate manufacturers, and technology platforms better remove and prevent this content from harming the public.

SUBMITTER: Mackey TK

PROVIDER: S-EPMC7451110 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Big Data, Natural Language Processing, and Deep Learning to Detect and Characterize Illicit COVID-19 Product Sales: Infoveillance Study on Twitter and Instagram.

Mackey Tim Ken TK Li Jiawei J Purushothaman Vidya V Nali Matthew M Shah Neal N Bardier Cortni C Cai Mingxiang M Liang Bryan B

JMIR public health and surveillance 20200825 3

<h4>Background</h4>The coronavirus disease (COVID-19) pandemic is perhaps the greatest global health challenge of the last century. Accompanying this pandemic is a parallel "infodemic," including the online marketing and sale of unapproved, illegal, and counterfeit COVID-19 health products including testing kits, treatments, and other questionable "cures." Enabling the proliferation of this content is the growing ubiquity of internet-based technologies, including popular social media platforms t ...[more]

PMID: 32750006

Similar Datasets

Project description:BackgroundThe coronavirus disease (COVID-19) pandemic is a global health emergency with over 6 million cases worldwide as of the beginning of June 2020. The pandemic is historic in scope and precedent given its emergence in an increasingly digital era. Importantly, there have been concerns about the accuracy of COVID-19 case counts due to issues such as lack of access to testing and difficulty in measuring recoveries.ObjectiveThe aims of this study were to detect and characterize user-generated conversations that could be associated with COVID-19-related symptoms, experiences with access to testing, and mentions of disease recovery using an unsupervised machine learning approach.MethodsTweets were collected from the Twitter public streaming application programming interface from March 3-20, 2020, filtered for general COVID-19-related keywords and then further filtered for terms that could be related to COVID-19 symptoms as self-reported by users. Tweets were analyzed using an unsupervised machine learning approach called the biterm topic model (BTM), where groups of tweets containing the same word-related themes were separated into topic clusters that included conversations about symptoms, testing, and recovery. Tweets in these clusters were then extracted and manually annotated for content analysis and assessed for their statistical and geographic characteristics.ResultsA total of 4,492,954 tweets were collected that contained terms that could be related to COVID-19 symptoms. After using BTM to identify relevant topic clusters and removing duplicate tweets, we identified a total of 3465 (<1%) tweets that included user-generated conversations about experiences that users associated with possible COVID-19 symptoms and other disease experiences. These tweets were grouped into five main categories including first- and secondhand reports of symptoms, symptom reporting concurrent with lack of testing, discussion of recovery, confirmation of negative COVID-19 diagnosis after receiving testing, and users recalling symptoms and questioning whether they might have been previously infected with COVID-19. The co-occurrence of tweets for these themes was statistically significant for users reporting symptoms with a lack of testing and with a discussion of recovery. A total of 63% (n=1112) of the geotagged tweets were located in the United States.ConclusionsThis study used unsupervised machine learning for the purposes of characterizing self-reporting of symptoms, experiences with testing, and mentions of recovery related to COVID-19. Many users reported symptoms they thought were related to COVID-19, but they were not able to get tested to confirm their concerns. In the absence of testing availability and confirmation, accurate case estimations for this period of the outbreak may never be known. Future studies should continue to explore the utility of infoveillance approaches to estimate COVID-19 disease severity.

Project description:BACKGROUND:On December 6 and 7, 2017, the US Department of Health and Human Services (HHS) hosted its first Code-a-Thon event aimed at leveraging technology and data-driven solutions to help combat the opioid epidemic. The authors—an interdisciplinary team from academia, the private sector, and the US Centers for Disease Control and Prevention—participated in the Code-a-Thon as part of the prevention track. OBJECTIVE:The aim of this study was to develop and deploy a methodology using machine learning to accurately detect the marketing and sale of opioids by illicit online sellers via Twitter as part of participation at the HHS Opioid Code-a-Thon event. METHODS:Tweets were collected from the Twitter public application programming interface stream filtered for common prescription opioid keywords in conjunction with participation in the Code-a-Thon from November 15, 2017 to December 5, 2017. An unsupervised machine learning–based approach was developed and used during the Code-a-Thon competition (24 hours) to obtain a summary of the content of the tweets to isolate those clusters associated with illegal online marketing and sale using a biterm topic model (BTM). After isolating relevant tweets, hyperlinks associated with these tweets were reviewed to assess the characteristics of illegal online sellers. RESULTS:We collected and analyzed 213,041 tweets over the course of the Code-a-Thon containing keywords codeine, percocet, vicodin, oxycontin, oxycodone, fentanyl, and hydrocodone. Using BTM, 0.32% (692/213,041) tweets were identified as being associated with illegal online marketing and sale of prescription opioids. After removing duplicates and dead links, we identified 34 unique “live” tweets, with 44% (15/34) directing consumers to illicit online pharmacies, 32% (11/34) linked to individual drug sellers, and 21% (7/34) used by marketing affiliates. In addition to offering the “no prescription” sale of opioids, many of these vendors also sold other controlled substances and illicit drugs. CONCLUSIONS:The results of this study are in line with prior studies that have identified social media platforms, including Twitter, as a potential conduit for supply and sale of illicit opioids. To translate these results into action, authors also developed a prototype wireframe for the purposes of detecting, classifying, and reporting illicit online pharmacy tweets selling controlled substances illegally to the US Food and Drug Administration and the US Drug Enforcement Agency. Further development of solutions based on these methods has the potential to proactively alert regulators and law enforcement agencies of illegal opioid sales, while also making the online environment safer for the public.

Project description:BackgroundBlack women in the United States disproportionately suffer adverse pregnancy and birth outcomes compared to White women. Economic adversity and implicit bias during clinical encounters may lead to physiological responses that place Black women at higher risk for adverse birth outcomes. The novel coronavirus disease of 2019 (COVID-19) further exacerbated this risk, as safety protocols increased social isolation in clinical settings, thereby limiting opportunities to advocate for unbiased care. Twitter, 1 of the most popular social networking sites, has been used to study a variety of issues of public interest, including health care. This study considers whether posts on Twitter accurately reflect public discourse during the COVID-19 pandemic and are being used in infodemiology studies by public health experts.ObjectiveThis study aims to assess the feasibility of Twitter for identifying public discourse related to social determinants of health and advocacy that influence maternal health among Black women across the United States and to examine trends in sentiment between 2019 and 2020 in the context of the COVID-19 pandemic.MethodsTweets were collected from March 1 to July 13, 2020, from 21 organizations and influencers and from 4 hashtags that focused on Black maternal health. Additionally, tweets from the same organizations and hashtags were collected from the year prior, from March 1 to July 13, 2019. Twint, a Python programming library, was used for data collection and analysis. We gathered the text of approximately 17,000 tweets, as well as all publicly available metadata. Topic modeling and k-means clustering were used to analyze the tweets.ResultsA variety of trends were observed when comparing the 2020 data set to the 2019 data set from the same period. The percentages listed for each topic are probabilities of that topic occurring in our corpus. In our topic models, tweets on reproductive justice, maternal mortality crises, and patient care increased by 67.46% in 2020 versus 2019. Topics on community, advocacy, and health equity increased by over 30% in 2020 versus 2019. In contrast, tweet topics that decreased in 2020 versus 2019 were as follows: tweets on Medicaid and medical coverage decreased by 27.73%, and discussions about creating space for Black women decreased by just under 30%.ConclusionsThe results indicate that the COVID-19 pandemic may have spurred an increased focus on advocating for improved reproductive health and maternal health outcomes among Black women in the United States. Further analyses are needed to capture a longer time frame that encompasses more of the pandemic, as well as more diverse voices to confirm the robustness of the findings. We also concluded that Twitter is an effective source for providing a snapshot of relevant topics to guide Black maternal health advocacy efforts.

Project description:BackgroundSocial media plays a major role in the daily life of adolescents and has become highly interesting for healthcare research as well. The aim of this study was to explore the social perception of orthodontic-related posts on Twitter and Instagram by young adults.Methods401 orthodontic-related posts were collected during a 30-day period and categorized with regard to specific characteristics - their content and the social networking site (SNS) being used as well as the presence or absence of a selfie. In order to investigate the social perception of these posts, 42 young adults rated the emotional states of the SNS users using the Self-Assessment Manikin (SAM)-Tool. A total of 4211 poster-rater observations pertaining to the three SAMs dimensions pleasure, arousal and dominance were analyzed by using linear and multinomial logistic regression analyses.ResultsThe investigated characteristics of the collected posts had significant effects on the perceived emotional state of the SNS users. Besides significant SNS-associated differences, there were also effects that were independent of the SNS being used: Receiving orthodontic appliances was more often associated with rather negative emotions (p < 0.001), while users who posted about the removal of such braces were more often perceived as joyful (p < 0.001). Interestingly, users whose posts contained selfies with visible braces were perceived as significantly more positive and stronger in comparison to users who did not post a picture of themselves (p < 0.05).ConclusionThis research gives insights into the social perception of orthodontic-related posts on SNS. While users' emotional states were perceived highly differential on both SNS, orthodontic-related content also revealed significant effects on social perception. Because selfies with visible braces were associated with positive feelings by young adults, a modern and SNS-related way of coping with a temporary supposed impairment like fixed orthodontic appliances might have been revealed through this research.

Project description:BackgroundOpioid use disorder and its consequences are a persistent public health concern for Australians. Web activity has been used to understand the perception of drug safety and diversion of drugs in contexts outside of Australia. The anonymity of the internet offers several advantages for surveilling and inquiring about specific covert behaviors, such as diversion or discussion of sensitive subjects where traditional surveillance approaches might be limited.ObjectiveThis study aims to characterize the content of web posts and compare reports of illicit sales of tapentadol and oxycodone from sources originating in Australia. First, post content is evaluated to determine whether internet discussion encourages or discourages proper therapeutic use of the drugs. Second, we hypothesize that tapentadol would have lower street price and fewer illicit sales than oxycodone.MethodsWeb posts originating in Australia between 2017 and 2019 were collected using the Researched Abuse, Diversion, and Addiction-Related Surveillance System Web Monitoring Program. Using a manual coding process, unstructured post content from social media, blogs, and forums was categorized into topics of discussion related to the harms and behaviors that could lead to harm. Illicit sales data in a structured format were collected through a crowdsourcing website between 2016 and 2019 using the Researched Abuse, Diversion, and Addiction-Related Surveillance System StreetRx Program. In total, 2 multivariable regression models assessed the differences in illicit price and number of sales.ResultsA total of 4.7% (28/600) of tapentadol posts discussed an adverse event, whereas 10.27% (95% CI 9.32-11.21) of oxycodone posts discussed this topic. A total of 10% (60/600) of tapentadol posts discussed unsafe use or side effects, whereas 20.17% (95% CI 18.92-21.41) of oxycodone posts discussed unsafe use or side effects. There were 31 illicit sales reports for tapentadol (geometric mean price per milligram: Aus $0.12 [US $0.09]) and 756 illicit sales reports for oxycodone (Aus $1.28 [US $0.91]). Models detected no differences in the street price or number of sales between the drugs when covariates were included, although the potency of the pill significantly predicted the street price (P<.001) and availability predicted the number of sales (P=.03).ConclusionsAustralians searching the web for opinions could judge tapentadol as safer than oxycodone because of the web post content. The illicit sales market for tapentadol was smaller than that of oxycodone, and drug potency and licit availability are likely important factors influencing the illicit market.

Project description:BackgroundSocial media use is now ubiquitous, but the growth in social media communications has also made it a convenient digital platform for drug dealers selling controlled substances, opioids, and other illicit drugs. Previous studies and news investigations have reported the use of popular social media platforms as conduits for opioid sales. This study uses deep learning to detect illicit drug dealing on the image and video sharing platform Instagram.ObjectiveThe aim of this study was to develop and evaluate a machine learning approach to detect Instagram posts related to illegal internet drug dealing.MethodsIn this paper, we describe an approach to detect drug dealers by using a deep learning model on Instagram. We collected Instagram posts using a Web scraper between July 2018 and October 2018 and then compared our deep learning model against 3 different machine learning models (eg, random forest, decision tree, and support vector machine) to assess the performance and accuracy of the model. For our deep learning model, we used the long short-term memory unit in the recurrent neural network to learn the pattern of the text of drug dealing posts. We also manually annotated all posts collected to evaluate our model performance and to characterize drug selling conversations.ResultsFrom the 12,857 posts we collected, we detected 1228 drug dealer posts comprising 267 unique users. We used cross-validation to evaluate the 4 models, with our deep learning model reaching 95% on F1 score and performing better than the other 3 models. We also found that by removing the hashtags in the text, the model had better performance. Detected posts contained hashtags related to several drugs, including the controlled substance Xanax (1078/1228, 87.78%), oxycodone/OxyContin (321/1228, 26.14%), and illicit drugs lysergic acid diethylamide (213/1228, 17.34%) and 3,4-methylenedioxy-methamphetamine (94/1228, 7.65%). We also observed the use of communication applications for suspected drug trading through user comments.ConclusionsOur approach using a combination of Web scraping and deep learning was able to detect illegal online drug sellers on Instagram, with high accuracy. Despite increased scrutiny by regulators and policymakers, the Instagram platform continues to host posts from drug dealers, in violation of federal law. Further action needs to be taken to ensure the safety of social media communities and help put an end to this illicit digital channel of sourcing.

Dataset Information

Big Data, Natural Language Processing, and Deep Learning to Detect and Characterize Illicit COVID-19 Product Sales: Infoveillance Study on Twitter and Instagram.

Publications

Big Data, Natural Language Processing, and Deep Learning to Detect and Characterize Illicit COVID-19 Product Sales: Infoveillance Study on Twitter and Instagram.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets