Illicit COVID-19 Product Sales
on Twitter and Instagram
The COVID-19 pandemic is one of the greatest global health crises of our times. One of the biggest challenges for public health experts has been the “infodemic”: the online marketing and sale of unapproved, illegal and/or counterfeit COVID-19 products such as testing kits, treatments and questionable “cures” that have spread throughout the Internet, including social media platforms.
In this report, ACCO expert Tim Mackay and his team aimed to develop big data, natural language processing and deep learning processes to better collect, identify and report fake, counterfeit and unapproved COVID-19 products from Twitter and Instagram.
Using a combination of web scraping on Instagram and filtering the public streaming on Twitter, Mackay and his team collected 6,029,323 tweets and 204,597 Instagram posts related to the marketing and sale of COVID-19 products. Then, after applying natural language processing and deep learning approaches, Mackay identified 1271 tweets and 596 Instagram posts associated with questionable COVID-19 products.
This data has been organized into a customized dashboard to help public health agencies, regulatory authorities, legitimate manufacturers and technology platforms better remove and prevent this content from harming the public.
Authors:
Tim K Mackey
Jiawei Li
Vidya Purushothaman
Matthew Nali
Neal Shah
Cortni Bardier
Mingxiang Cai
Bryan Liang