Michael Chary1, Nicholas Genes2, Christophe Giraud-Carrier3, Carl Hanson4, Lewis S Nelson5, Alex F Manini6,7. 1. Department of Emergency Medicine, NewYork-Presbyterian/Queens, Queens, NY, USA. mic9180@nyp.org. 2. Department of Emergency Medicine, Mount Sinai Hospital, New York, NY, USA. 3. Department of Computer Science, Brigham Young University, Provo, UT, USA. 4. Department of Health Science, Brigham Young University, Provo, UT, USA. 5. Department of Emergency Medicine, Rutgers New Jersey Medical School, Newark, NJ, USA. 6. Division of Medical Toxicology, The Icahn School of Medicine, New York, NY, USA. 7. Department of Emergency Medicine, Elmhurst Hospital Center, Queens, NY, USA.
Abstract
BACKGROUND: The misuse of prescription opioids (MUPO) is a leading public health concern. Social media are playing an expanded role in public health research, but there are few methods for estimating established epidemiological metrics from social media. The purpose of this study was to demonstrate that the geographic variation of social media posts mentioning prescription opioid misuse strongly correlates with government estimates of MUPO in the last month. METHODS: We wrote software to acquire publicly available tweets from Twitter from 2012 to 2014 that contained at least one keyword related to prescription opioid use (n = 3,611,528). A medical toxicologist and emergency physician curated the list of keywords. We used the semantic distance (SemD) to automatically quantify the similarity of meaning between tweets and identify tweets that mentioned MUPO. We defined the SemD between two words as the shortest distance between the two corresponding word-centroids. Each word-centroid represented all recognized meanings of a word. We validated this automatic identification with manual curation. We used Twitter metadata to estimate the location of each tweet. We compared our estimated geographic distribution with the 2013-2015 National Surveys on Drug Usage and Health (NSDUH). RESULTS: Tweets that mentioned MUPO formed a distinct cluster far away from semantically unrelated tweets. The state-by-state correlation between Twitter and NSDUH was highly significant across all NSDUH survey years. The correlation was strongest between Twitter and NSDUH data from those aged 18-25 (r = 0.94, p < 0.01 for 2012; r = 0.94, p < 0.01 for 2013; r = 0.71, p = 0.02 for 2014). The correlation was driven by discussions of opioid use, even after controlling for geographic variation in Twitter usage. CONCLUSIONS: Mentions of MUPO on Twitter correlate strongly with state-by-state NSDUH estimates of MUPO. We have also demonstrated that a natural language processing can be used to analyze social media to provide insights for syndromic toxicosurveillance.
BACKGROUND: The misuse of prescription opioids (MUPO) is a leading public health concern. Social media are playing an expanded role in public health research, but there are few methods for estimating established epidemiological metrics from social media. The purpose of this study was to demonstrate that the geographic variation of social media posts mentioning prescription opioid misuse strongly correlates with government estimates of MUPO in the last month. METHODS: We wrote software to acquire publicly available tweets from Twitter from 2012 to 2014 that contained at least one keyword related to prescription opioid use (n = 3,611,528). A medical toxicologist and emergency physician curated the list of keywords. We used the semantic distance (SemD) to automatically quantify the similarity of meaning between tweets and identify tweets that mentioned MUPO. We defined the SemD between two words as the shortest distance between the two corresponding word-centroids. Each word-centroid represented all recognized meanings of a word. We validated this automatic identification with manual curation. We used Twitter metadata to estimate the location of each tweet. We compared our estimated geographic distribution with the 2013-2015 National Surveys on Drug Usage and Health (NSDUH). RESULTS:Tweets that mentioned MUPO formed a distinct cluster far away from semantically unrelated tweets. The state-by-state correlation between Twitter and NSDUH was highly significant across all NSDUH survey years. The correlation was strongest between Twitter and NSDUH data from those aged 18-25 (r = 0.94, p < 0.01 for 2012; r = 0.94, p < 0.01 for 2013; r = 0.71, p = 0.02 for 2014). The correlation was driven by discussions of opioid use, even after controlling for geographic variation in Twitter usage. CONCLUSIONS: Mentions of MUPO on Twitter correlate strongly with state-by-state NSDUH estimates of MUPO. We have also demonstrated that a natural language processing can be used to analyze social media to provide insights for syndromic toxicosurveillance.
Entities:
Keywords:
Computational linguistics; Epidemiology; Misuse; Natural language processing; Opioids; Social media
Authors: Johannes C Eichstaedt; Hansen Andrew Schwartz; Margaret L Kern; Gregory Park; Darwin R Labarthe; Raina M Merchant; Sneha Jha; Megha Agrawal; Lukasz A Dziurzynski; Maarten Sap; Christopher Weeg; Emily E Larson; Lyle H Ungar; Martin E P Seligman Journal: Psychol Sci Date: 2015-01-20
Authors: Scott H Burton; Kesler W Tanner; Christophe G Giraud-Carrier; Joshua H West; Michael D Barnes Journal: J Med Internet Res Date: 2012-11-15 Impact factor: 5.428
Authors: Thiago D Nascimento; Marcos F DosSantos; Theodora Danciu; Misty DeBoer; Hendrik van Holsbeeck; Sarah R Lucas; Christine Aiello; Leen Khatib; MaryCatherine A Bender; Jon-Kar Zubieta; Alexandre F DaSilva Journal: J Med Internet Res Date: 2014-04-03 Impact factor: 5.428
Authors: Christophe Lemey; Aziliz Le Glaz; Yannis Haralambous; Deok-Hee Kim-Dufor; Philippe Lenca; Romain Billot; Taylor C Ryan; Jonathan Marsh; Jordan DeVylder; Michel Walter; Sofian Berrouiguet Journal: J Med Internet Res Date: 2021-05-04 Impact factor: 5.428
Authors: Jennifer S Gewandter; Shannon M Smith; Robert H Dworkin; Dennis C Turk; Tong J Gan; Ian Gilron; Sharon Hertz; Nathaniel P Katz; John D Markman; Srinivasa N Raja; Michael C Rowbotham; Brett R Stacey; Eric C Strain; Denham S Ward; John T Farrar; Kurt Kroenke; James P Rathmell; Richard Rauck; Colville Brown; Penney Cowan; Robert R Edwards; James C Eisenach; McKenzie Ferguson; Roy Freeman; Roy Gray; Kathryn Giblin; Hanna Grol-Prokopczyk; Jennifer Haythornthwaite; Robert N Jamison; Marc Martel; Ewan McNicol; Michael L Oshinsky; Friedhelm Sandbrink; Joachim Scholz; Richard Scranton; Lee S Simon; Deborah Steiner; Kenneth Verburg; Ajay D Wasan; Kerry Wentworth Journal: Pain Date: 2021-11-01 Impact factor: 7.926