Exploring trends of nonmedical use of prescription drugs and polydrug abuse in the Twittersphere using unsupervised machine learning

详细信息    查看全文

• 作者：Janani Kalyanam^a ; Takeo Katsuki^b ; Gert R.G. Lanckriet^a ; Tim K. Mackey^c ; ^d ; ^e ; ^{tmackey@ucsd.edu}
• 关键词：Nonmedical use of prescription drugs ; Prescription opioid abuse ; Digital surveillance ; Substance abuse ; Twitter ; Social media
• 刊名：Addictive Behaviors
• 出版年：2017
• 出版时间：February 2017
• 年：2017
• 卷：65
• 期：Complete
• 页码：289-295
• 全文大小：289 K
• 卷排序：65

文摘

A methodology using unsupervised machine learning analyzed 11 million tweets filtered for commonly abused prescription opioid drugs Analyses identified 2.3 million tweets with content relevant to nonmedical use of prescription medications/drugs (NMUPD) Twitter content was associated with a high degree of discussion (approximately 80%) about polydrug abuse involving multiple types of substances The methodology can filter large volumes of twitter data with minimal human intervention to identify macro NMUPD themes and trends