Cannabis remains one of the most commonly used psychoactive substances in the United States, and current epidemiological studies indicate broadening acceptability. This aim of this project is to decrease the burden of psychoactive substance use in the US.
The three-year study will develop and deploy eDrugTrends, an innovative platform for semi-automated processing of social media data, to track trends in cannabis and synthetic cannabinoid use, identify opinion leaders and assess differences across US regions with varying cannabis legalization policies.
Social media data sources will include Twitter and at least five web forums. The study will integrate quantitative and qualitative methods, and will employ targeted, anonymous surveys on web forums to complement and triangulate analysis of user-generated content.
Associate Professor Raminta Daniulaityte, Wright State University, Ohio, United States
Professor Edward W. Boyer, University of Massachusetts Medical School, United States
Professor Robert G. Carlson, Wright State University, Ohio, United States
Associate Professor Silvia Martins, Columbia University, New York, United States
Assistant Professor Ramzi W. Nahhas, Wright State University, Ohio, United States
Professor Amit Sheth, Wright State University, Ohio, United States
Professor Krishnaprasad Thirunarayan, Wright State University, Ohio, United States
Cannabis remains one of the most commonly used psychoactive substances in the U.S., and current epidemiological studies indicate broadening acceptability. Over the past several years, synthetic cannabinoids (“synthetics,” such as Spice, K2) have emerged as new designer drugs. Synthetics, after gaining popularity as “legal” alternatives to cannabis, have been associated with adverse health effects such as seizures and changes in mental status requiring ICU admission. In the context of profound changes in cannabis legalization policies that are taking place across the U.S., close epidemiological monitoring of natural and synthetic cannabinoid products is needed to assess the impact of policy changes and identify emerging issues and trends.
Web 2.0 empowered social media platforms such as Twitter and Web forums have opened up new venues for individuals to freely share their drug use experiences and post questions, comments, and opinions about different drugs. Content analysis of such tweets and Web forum posts can provide valuable insights about drug user behaviors and attitudes. Content analysis can be extended to include temporal, geographic, and social network dimensions of social media data to track changes over time, examine regional differences, and to identify opinion leaders who influence attitudes and behaviors associated with cannabis and synthetic cannabinoid use. However, because of the volume and challenges introduced by web-based data, social media sources remain largely under-utilized in drug abuse research.
This multi-PI study will integrate cutting-edge information processing techniques, such as the Semantic Web, Natural Language Processing (NLP), and Machine Learning (ML), to advance the analysis of social media data for drug abuse epidemiology research. Our multidisciplinary framework builds on the successes of our collaborative R21 (DA030571) and strong representation in all key areas—substance abuse epidemiology, statistical and qualitative methods, drug abuse toxicology, and state-of-the-art computational and engineering expertise.
Specific Aim 1: Develop a comprehensive software platform, eDrugTrends, for semi-automated processing and visualization of thematic, sentiment, spatio-temporal, and social network dimensions of social media data (Twitter and Web forums) on cannabis and synthetic cannabinoid use.
Specific Aim 2: Deploy eDrugTrends to:
- Identify and compare trends in knowledge, attitudes, and behaviors related to cannabis and synthetic cannabinoid use across U.S. regions with different cannabis legalization policies using Twitter and Web forum data.
- Analyze social network characteristics and identify key influencers (opinions leaders) in cannabis and synthetic cannabinoid-related discussions on Twitter.
We will build on the existing infrastructure developed by our research team: 1) Twitris, a computer platform designed to analyze Twitter data;24-27 and 2) PREDOSE, a computer platform, developed for our collaborative R21 (DA030571) to analyze Web forum data on illegal buprenorphine use.28,29 Key elements of Twitris and PREDOSE will be adapted and enhanced to develop eDrugTrends, a comprehensive and highly scalable software platform, equipped to process real-time social media data, semi-automate information extraction about knowledge, attitudes and behaviors related to cannabis and synthetic cannabinoid use, and to produce iterative maps and graphical images of drug trends and social (or cyber) networks.
The eDrugTrends platform has been refined and can now be used to track trends in cannabis and synthetic cannabis use and harms. Dr Barratt visited the team in Dayton, Ohio, in November 2015, and saw the platform in operation. A survey of web forum users focusing on the use of cannabis concentrates (‘dabs’) was conducted in 2016. This survey was informed by the analyses of trends through the eDrugTrends platform. Write up of analysis is underway.
Publications arising from this project are expected to be published in 2017.
Publications arising from this project are expected to be published in 2017.
Our study is highly significant in two senses: 1) First, the development of eDrugTrends will advance the field’s technological and methodological capabilities to harness social media sources for drug abuse surveillance research. 2) Second, our deployment of the platform will inform the field on new trends regarding the use of cannabis and synthetic cannabinoids. The key innovation of our approach is the creative adaptation of the state-of-the art technological advancements in computer science and engineering to meet the unique needs and challenges of drug abuse research. eDrugTrends will have high public health impact by providing a tool that can be used to inform more timely interventions and policy responses to changes in cannabis and synthetic cannabinoid use and associated harms.