A group of researchers including Tim K. Mackey , Janani Kalyanam , Takeo Katsuki and Gert Lanckriet, all from San Diego have created a Machine Learning (Artificial Intelligence) to detect Prescription Opioid Abuse Promotion and Access though Twitter.
NOTE: Opioids are drugs that act on the nervous system to relieve pain. Continued use and abuse can be very dangerous. Example of an opioid is Morphine.
The objective of the research team as found on their paper is to "deploy a methodology accurately identifying tweets marketing the illegal online sale of controlled substances" .
Methods employed by the research team.
In their paper, the research team made it known that the method employed is to collect tweets from the Twitter public API (Application Program Interface) stream filtered specifically for prescription opioid keywords. The team then use unsupervised machine learning (topic modeling) to identify and locate topics associated with illegal online marketing and sales of drugs.
CHECK: What is the meaning of Deep Learning?
The team conducted Web Forensic analyses to characterize different types of online vendors.
We analyzed 619 937 tweets containing the keywords codeine, Percocet, fentanyl, Vicodin, Oxycontin, oxycodone, and hydrocodone over a 5-month period from June to November 2015.
The team concluded that their methodology can be used to identify illegal online drug sellers.
Results of the research
A total of 1778 tweets (< 1%) were identified as marketing the sale of controlled substances online; 90% had imbedded hyperlinks, but only 46 were “live” at the time of the evaluation. Seven distinct URLs linked to Web sites marketing or illegally selling controlled substances online.You can find out more on this Publication By The American Public Health Association