Detecting Novel and Emerging Drug Terms Using Natural Language Processing: A Social Media Corpus Study

Abstract

BackgroundWith the rapid development of new psychoactive substances (NPS) and changes in the use of more traditional drugs, it is increasingly difficult for researchers and public health practitioners to keep up with emerging drugs and drug terms. Substance use surveys and diagnostic tools need to be able to ask about substances using the terms that drug users themselves are likely to be using. Analyses of social media may offer new ways for researchers to uncover and track changes in drug terms in near real time. This study describes the initial results from an innovative collaboration between substance use epidemiologists and linguistic scientists employing techniques from the field of natural language processing to examine drug-related terms in a sample of tweets from the United States.ObjectiveThe objective of this study was to assess the feasibility of using distributed word-vector embeddings trained on social media data to uncover previously unknown (to researchers) drug terms.MethodsIn this pilot study, we trained a continuous bag of words (CBOW) model of distributed word-vector embeddings on a Twitter dataset collected during July 2016 (roughly 884.2 million tokens). We queried the trained word embeddings for terms with high cosine similarity (a proxy for semantic relatedness) to well-known slang terms for marijuana to produce a list of candidate terms likely to function as slang terms for this substance. This candidate list was then compared with an expert-generated list of marijuana terms to assess the accuracy and efficacy of using word-vector embeddings to search for novel drug terminology.ResultsThe method described here produced a list of 200 candidate terms for the target substance (marijuana). Of these 200 candidates, 115 were determined to in fact relate to marijuana (65 terms for the substance itself, 50 terms related to paraphernalia). This included 30 terms which were used to refer to the target substance in the corpus yet did not appear on the expert-generated list and were therefore considered to be successful cases of uncovering novel drug terminology. Several of these novel terms appear to have been introduced as recently as 1 or 2 months before the corpus time slice used to train the word embeddings.ConclusionsThough the precision of the method described here is low enough as to still necessitate human review of any candidate term lists generated in such a manner, the fact that this process was able to detect 30 novel terms for the target substance based only on one month’s worth of Twitter data is highly promising. We see this pilot study as an important proof of concept and a first step toward producing a fully automated drug term discovery system capable of tracking emerging NPS terms in real time.

Solution to Detect, Classify, and Report Illicit Online Marketing and Sales of Controlled Substances via Twitter: Using Machine Learning and Web Forensics to Combat Digital Opioid Access

“…To take this next step, funding with the primary aim of translating this research into MVP phase and eventual production and scale-up is needed (such as our recent award of an NIH NIDA 2017 “Start a SUD Startup” challenge, which provides small awards for startups related to substance abuse disorders with the aim of transitioning companies to a successful NIDA Small Business Innovation Research grant; see [ 65 ] for a recorded video discussing Code-a-Thon solution submitted as part of NIH NIDA 2017 “Start a SUD Startup” challenge grant). Additionally, we would need to automate data collection and backend analysis of Twitter data with integration via a Web application or software, while also developing solutions using natural processing language to automate classification of hyperlinks suspected as engaged in the sale of prescription opioids, techniques that have been explored in prior studies [ 23 , 66 , 67 ]. Finally, automated scripts that generate information needed for standardized reporting of results to the FDA and DEA via their online Web forms would also need to be developed.…”

Solution to Detect, Classify, and Report Illicit Online Marketing and Sales of Controlled Substances via Twitter: Using Machine Learning and Web Forensics to Combat Digital Opioid Access (Preprint)

“…Additionally, we would need to automate data collection and backend analysis of Twitter data with integration via a web application, while also developing solutions using natural processing language to automate classification of hyperlinks suspected as engaged in the sale of prescription opioids, techniques that have been explored in prior studies [22,45,46]. Finally, automated scripts that generate information needed for standardized reporting of results to the FDA and DEA via their online web forms would also need to be developed.…”

Sales and Advertising Channels of New Psychoactive Substances (NPS): Internet, Social Networks, and Smartphone Apps

“…All the users, indeed, can be part of a #highsociety, allowing them to share their #proudstoners daily states of mind. Very recently, epidemiologists and linguistic scientists used Twitter to test the feasibility of producing a fully-automated “drug term discovery” system capable of tracking emerging NPS terms in real time [ 49 ], which confirms that data collected on Twitter may be used to explore trends in NPS selling and use [ 50 ]. Along with other cyber drug communities (e.g., blogs, drug fora, Facebook), Twitter allowed the identification and characterization of a new generation of NPS users, the so-called “e-psychonauts”, that considered themselves as psychedelic researchers, mind navigators, or chemicals experimenters [ 51 ].…”