Machine learning IDs tweets marketing, selling opioids

Researchers from the University of California, San Diego have developed a machine learning tool to sort through Twitter to identify tweets illegally selling prescription opioids online, according to a study published in the American Journal of Public Health.

As the opioid epidemic in America spreads, researchers are looking to social media to detect illegal activities and reduce the number of people affected by opioid addiction. In this study, researchers utilize machine learning to pinpoint the selling of opioids on Twitter.

"An unhealthy use of prescription and non-prescription opioid drugs continues to rise in the United States. Public policy and law enforcement efforts are trying to address this crisis, but closer attention to the potential negative influence of digital technologies is needed," said Tim K. Mackey, PhD, UC, San Diego School of Medicine associate professor of anesthesiology and global public health and first author. "Our study demonstrates the utility of a technology to aid in these efforts that searches social media for behavior that poses a public threat, such as the illegal sale of controlled substances."

The study collected 619,937 tweets from June to November 2015 containing the words “codeine,” “Percocet,” “fentanyl,” “Vicodin,” “Oxycontin,” “oxycodone” and “hydrocodone” to identify 1,778 tweets marketing the sale of controlled substances. Of these tweets, 90 percent included a hyperlink to external websites but only 46 were still active when examined by researchers. Overall, seven distinct URLs were identified as leading to websites where the prescriptions could be purchased.

"In addition, social media providers can use it to find or prohibit content that is illegal or violates laws to ensure consumers have a safer experience online,” said Mackey. "The online sale of controlled substances is directly prohibited by federal law. However, social media appears to act as a conduit for increased risk to substance abuse behavior.”