Raminta Daniulaityte1,2, Francois R Lamy1,2, G Alan Smith2, Ramzi W Nahhas3,4, Robert G Carlson1,2, Krishnaprasad Thirunarayan2, Silvia S Martins5, Edward W Boyer6, Amit Sheth2. 1. Center for Interventions, Treatment, and Addictions Research (CITAR), Department of Population and Public Health Sciences, Wright State University Boonshoft School of Medicine, Dayton, Ohio. 2. Ohio Center of Excellence in Knowledge-Enabled Computing (Kno.e.sis), Department of Computer Science and Engineering, Wright State University, Dayton, Ohio. 3. Department of Population and Public Health Sciences, Wright State University Boonshoft School of Medicine, Dayton, Ohio. 4. Department of Psychiatry, Wright State University Boonshoft School of Medicine, Dayton, Ohio. 5. Department of Epidemiology, Columbia University Mailman School of Public Health, New York, New York. 6. Department of Emergency Medicine, Brigham and Women's Hospital, Boston, Massachusetts.
Abstract
OBJECTIVE: Twitter data offer new possibilities for tracking health-related communications. This study is among the first to apply advanced information processing to identify geographic and content features of cannabis-related tweeting in the United States. METHOD: Tweets were collected using streaming Application Programming Interface (March-May 2016) and were processed by eDrugTrends to identify geolocation and classify content by source (personal communication, media, retail) and sentiment (positive, negative, neutral). States were grouped by cannabis legalization policies into "recreational," "medical, less restrictive," "medical, more restrictive," and "illegal." Permutation tests were performed to analyze differences among four groups in adjusted percentages of all tweets, unique users, personal communications only, and positive-to-negative sentiment ratios. RESULTS: About 30% of all 13,233,837 cannabis-related tweets had identifiable state-level geo-information. Among geolocated tweets, 76.2% were personal communications, 21.1% media, and 2.7% retail. About 71% of personal communication tweets expressed positive sentiment toward cannabis; 16% expressed negative sentiment. States in the recreational group had significantly greater average adjusted percentage of cannabis tweets (3.01%) compared with other groups. For personal communication tweets only, the recreational group (2.47%) was significantly greater than the medical, more restrictive (1.84%) and illegal (1.85%) groups. Similarly, the recreational group had significantly greater average positive-to-negative sentiment ratio (4.64) compared with the medical, more restrictive (4.15) and illegal (4.19) groups. Average adjusted percentages of unique users showed similar differences between recreational and other groups. CONCLUSIONS: States with less restrictive policies displayed greater cannabis-related tweeting and conveyed more positive sentiment. The study demonstrates the potential of Twitter data to become a valuable indicator of drug-related communications in the context of varying policy environments.
OBJECTIVE: Twitter data offer new possibilities for tracking health-related communications. This study is among the first to apply advanced information processing to identify geographic and content features of cannabis-related tweeting in the United States. METHOD:Tweets were collected using streaming Application Programming Interface (March-May 2016) and were processed by eDrugTrends to identify geolocation and classify content by source (personal communication, media, retail) and sentiment (positive, negative, neutral). States were grouped by cannabis legalization policies into "recreational," "medical, less restrictive," "medical, more restrictive," and "illegal." Permutation tests were performed to analyze differences among four groups in adjusted percentages of all tweets, unique users, personal communications only, and positive-to-negative sentiment ratios. RESULTS: About 30% of all 13,233,837 cannabis-related tweets had identifiable state-level geo-information. Among geolocated tweets, 76.2% were personal communications, 21.1% media, and 2.7% retail. About 71% of personal communication tweets expressed positive sentiment toward cannabis; 16% expressed negative sentiment. States in the recreational group had significantly greater average adjusted percentage of cannabis tweets (3.01%) compared with other groups. For personal communication tweets only, the recreational group (2.47%) was significantly greater than the medical, more restrictive (1.84%) and illegal (1.85%) groups. Similarly, the recreational group had significantly greater average positive-to-negative sentiment ratio (4.64) compared with the medical, more restrictive (4.15) and illegal (4.19) groups. Average adjusted percentages of unique users showed similar differences between recreational and other groups. CONCLUSIONS: States with less restrictive policies displayed greater cannabis-related tweeting and conveyed more positive sentiment. The study demonstrates the potential of Twitter data to become a valuable indicator of drug-related communications in the context of varying policy environments.
Authors: Raminta Daniulaityte; Ramzi W Nahhas; Sanjaya Wijeratne; Robert G Carlson; Francois R Lamy; Silvia S Martins; Edward W Boyer; G Alan Smith; Amit Sheth Journal: Drug Alcohol Depend Date: 2015-08-22 Impact factor: 4.492
Authors: Raminta Daniulaityte; Lu Chen; Francois R Lamy; Robert G Carlson; Krishnaprasad Thirunarayan; Amit Sheth Journal: JMIR Public Health Surveill Date: 2016-10-24
Authors: Heather Cole-Lewis; Arun Varghese; Amy Sanders; Mary Schwarz; Jillian Pugatch; Erik Augustson Journal: J Med Internet Res Date: 2015-08-25 Impact factor: 5.428
Authors: Usha Lokala; Francois R Lamy; Raminta Daniulaityte; Amit Sheth; Ramzi W Nahhas; Jason I Roden; Shweta Yadav; Robert G Carlson Journal: Comput Math Organ Theory Date: 2018-10-25 Impact factor: 2.023
Authors: Raminta Daniulaityte; Mussa Y Zatreh; Francois R Lamy; Ramzi W Nahhas; Silvia S Martins; Amit Sheth; Robert G Carlson Journal: Drug Alcohol Depend Date: 2018-04-11 Impact factor: 4.492
Authors: Francois R Lamy; Raminta Daniulaityte; Monica J Barratt; Usha Lokala; Amit Sheth; Robert G Carlson Journal: Drug Alcohol Depend Date: 2020-06-12 Impact factor: 4.492