A team of medical researchers has developed artificial intelligence that can scan and identify signs of opioid abuse on Twitter, according to a report.
The team hopes that the AI could be used to find out the location and details of potential opioid abusers in an effort to combat addictions, which are increasing in the United States.
“Using artificially intelligent software they developed to analyze tweets and related geographic information, the researchers found Twitter to be a particularly reliable data source for pinpointing where the situation is at its worst,” reported the Scientific American. “With about 500 million messages posted to the microblogging site daily, such an approach could help alert local health officials so they can gather funding or other resources to tackle the issue.”
“The researchers wanted to know whether analyzing tweet text could help them estimate the location and relative prevalence of prescription opioid misuse as accurately as established epidemiologic studies—such as the National Survey on Drug Usage and Health (NSDUH)—in a fraction of the time,” they continued, adding, “Traditional medical research like the NSDUH can take years to complete and publish.”
According to the report, “Twitter users tend to write frequent, short messages on a wide variety of topics, and they often indicate their location and other demographic information.”
“We found that our estimates agreed with [NSDUH] data, suggesting that social media can be a reliable additional source of epidemiological data regarding substance use,” claimed emergency medicine physician Michael Chary. “We can analyze social media to canvass larger segments of the general population and potentially yield timely insights.”
“There’s a confessional effect… People may discuss or reveal things on social media that, when directly asked, they may not,” he explained. “There may be a level of candor there that’s not present in the emergency room or internist’s office.”
The AI, which was able to “quickly search more than 3.6 million tweets,” targeted keywords associated with opioid abuse, including “dope,” “percs,” “white,” “TNT” and “Captain Cody.”
Codeine, which is often referred to as “syrup,” had to be carefully sorted through to distinguish who was using the word to refer to drugs or breakfast.
“This work is most useful in capturing trends,” Chary concluded. “We all agree there is a problem with opioid use. It’s very difficult to conduct these federal surveys at any scale with the frequency needed to say, ‘Over the last three months drug use in this particular location is going up. What’s going on here?’”