Twitter-Based Detection of Illegal Online Sale of Prescription Opioid.
Objectives. To deploy a methodology accurately identifying tweets marketing the illegal online sale of controlled substances. Methods. We first collected tweets from the Twitter public application program interface stream filtered for prescription opioid keywords. We then used unsupervised machine l...
| Published in: | American Journal of Public Health Vol. 107; no. 12; pp. 1910 - 1916 |
|---|---|
| Main Authors: | , , , |
| Format: | Article |
| Published: |
American Public Health Association
Dec2017
|
| Subjects: | |
| Online Access: | View this record in EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=126116556&site=ehost-live header: @attributes: shortDbName: ssf uiTerm: 126116556 longDbName: Social Sciences Full Text (H.W. Wilson) uiTag: AN controlInfo: bkinfo: jinfo: jid: 00900036 APH jtl: American Journal of Public Health issn: 00900036 maglogo: N pubinfo: dt: Dec2017 vid: 107 iid: 12 pid: 44 pub: American Public Health Association artinfo: ui: 126116556 10.2105/AJPH.2017.303994 ppf: 1910 ppct: 6 formats: tig: atl: Twitter-Based Detection of Illegal Online Sale of Prescription Opioid. aug: au: Mackey, Tim K. Kalyanam, Janani Takeo Katsuki Lanckriet, Gert affil: Department of Anesthesiology, University of California, San Diego. Department of Medicine, University of California, San Diego. Global Health Policy Institute, San Diego. Global Health Policy Institute, University of California, San Diego. Department of Electrical and Computer Engineering, University of California, San Diego. Kavli Institute for Brain and Mind, University of California, San Diego. su: United States Twitter (Web resource) Drugs of abuse Prices Law Forensic sciences Narcotics World Wide Web Oxycodone Social media Controlled substances Opioids Internet sales Controlled substance laws Legal status of drug dealers Internet pharmacies Website laws Drug laws Fentanyl Codeine Rating of sales personnel Mobile apps Descriptive statistics sug: subj: Drugs of abuse Prices Law Forensic sciences Narcotics World Wide Web Oxycodone Social media Controlled substances United States Medicinal and Botanical Manufacturing Pharmaceutical and medicine manufacturing Pharmaceutical Preparation Manufacturing Drugs and Druggists' Sundries Merchant Wholesalers Pharmaceuticals and pharmacy supplies merchant wholesalers Internet Publishing and Broadcasting and Web Search Portals Electronic Shopping Opioids Internet sales Controlled substance laws Legal status of drug dealers Internet pharmacies Website laws Drug laws Fentanyl Codeine Rating of sales personnel Mobile apps Descriptive statistics Twitter (Web resource) ab: Objectives. To deploy a methodology accurately identifying tweets marketing the illegal online sale of controlled substances. Methods. We first collected tweets from the Twitter public application program interface stream filtered for prescription opioid keywords. We then used unsupervised machine learning (specifically, topic modeling) to identify topics associated with illegal online marketing and sales. Finally, we 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. Results. 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. Conclusions. Our methodology can identify illegal online sale of prescription opioids from large volumes of tweets. Our results indicate that controlled substances are trafficked online via different strategies and vendors. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: N holdings: @attributes: islocal: N |
|---|