Mining social media data on marijuana use for Post Traumatic Stress Disorder

Hongying Dai, Jianqiang Hao

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Background We seek to evaluate factors that could potentially impact the public's attitudes to PTSD related marijuana use on Twitter. Methods We collected tweets that contained the “PTSD” and “Post Trauma Stress Disorder” from August 1, 2015 to April 15, 2016 (n = 1,253,872 tweets). A Naïve Bayes model was constructed to classify tweets into two opinion polarities (support vs. neutral/against marijuana use for PTSD). Results The marijuana related tweets were predominated by the supporting opinions (89.6%). The public opinions about marijuana use for PTSD on Twitter were significantly associated with state-level legislation. States that legalized medical and recreational marijuana use had the highest prevalence of support tweets (1.3 ± 0.6), followed by the states that legalized medical but not recreational use (0.5 ± 0.3) and the states that had no laws legalizing marijuana (0.2 ± 0.1, p < 0.0001). A higher prevalence of support tweets was associated with states with a lower proportion of youth (r = −0.35, p = 0.01) and a higher education rate (r = 0.38, p = 0.006). Conclusion Twitter data suggest a proliferation of supporting marijuana use for PTSD treatments, especially in the states that legalized medical and/or recreational use of marijuana.

Original languageEnglish (US)
Pages (from-to)282-290
Number of pages9
JournalComputers in Human Behavior
Volume70
DOIs
StatePublished - May 1 2017
Externally publishedYes

Fingerprint

Social Media
Cannabis
Post-Traumatic Stress Disorders
Education
Medical Marijuana
Public Opinion
Legislation
Wounds and Injuries

Keywords

  • Marijuana
  • PTSD
  • Socio-economic factors
  • State-level legalization
  • Twitter

ASJC Scopus subject areas

  • Arts and Humanities (miscellaneous)
  • Human-Computer Interaction
  • Psychology(all)

Cite this

Mining social media data on marijuana use for Post Traumatic Stress Disorder. / Dai, Hongying; Hao, Jianqiang.

In: Computers in Human Behavior, Vol. 70, 01.05.2017, p. 282-290.

Research output: Contribution to journalArticle

@article{2eaca4f04e9d4aa8b2b95a3bbf33a7ce,
title = "Mining social media data on marijuana use for Post Traumatic Stress Disorder",
abstract = "Background We seek to evaluate factors that could potentially impact the public's attitudes to PTSD related marijuana use on Twitter. Methods We collected tweets that contained the “PTSD” and “Post Trauma Stress Disorder” from August 1, 2015 to April 15, 2016 (n = 1,253,872 tweets). A Na{\"i}ve Bayes model was constructed to classify tweets into two opinion polarities (support vs. neutral/against marijuana use for PTSD). Results The marijuana related tweets were predominated by the supporting opinions (89.6{\%}). The public opinions about marijuana use for PTSD on Twitter were significantly associated with state-level legislation. States that legalized medical and recreational marijuana use had the highest prevalence of support tweets (1.3 ± 0.6), followed by the states that legalized medical but not recreational use (0.5 ± 0.3) and the states that had no laws legalizing marijuana (0.2 ± 0.1, p < 0.0001). A higher prevalence of support tweets was associated with states with a lower proportion of youth (r = −0.35, p = 0.01) and a higher education rate (r = 0.38, p = 0.006). Conclusion Twitter data suggest a proliferation of supporting marijuana use for PTSD treatments, especially in the states that legalized medical and/or recreational use of marijuana.",
keywords = "Marijuana, PTSD, Socio-economic factors, State-level legalization, Twitter",
author = "Hongying Dai and Jianqiang Hao",
year = "2017",
month = "5",
day = "1",
doi = "10.1016/j.chb.2016.12.064",
language = "English (US)",
volume = "70",
pages = "282--290",
journal = "Computers in Human Behavior",
issn = "0747-5632",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Mining social media data on marijuana use for Post Traumatic Stress Disorder

AU - Dai, Hongying

AU - Hao, Jianqiang

PY - 2017/5/1

Y1 - 2017/5/1

N2 - Background We seek to evaluate factors that could potentially impact the public's attitudes to PTSD related marijuana use on Twitter. Methods We collected tweets that contained the “PTSD” and “Post Trauma Stress Disorder” from August 1, 2015 to April 15, 2016 (n = 1,253,872 tweets). A Naïve Bayes model was constructed to classify tweets into two opinion polarities (support vs. neutral/against marijuana use for PTSD). Results The marijuana related tweets were predominated by the supporting opinions (89.6%). The public opinions about marijuana use for PTSD on Twitter were significantly associated with state-level legislation. States that legalized medical and recreational marijuana use had the highest prevalence of support tweets (1.3 ± 0.6), followed by the states that legalized medical but not recreational use (0.5 ± 0.3) and the states that had no laws legalizing marijuana (0.2 ± 0.1, p < 0.0001). A higher prevalence of support tweets was associated with states with a lower proportion of youth (r = −0.35, p = 0.01) and a higher education rate (r = 0.38, p = 0.006). Conclusion Twitter data suggest a proliferation of supporting marijuana use for PTSD treatments, especially in the states that legalized medical and/or recreational use of marijuana.

AB - Background We seek to evaluate factors that could potentially impact the public's attitudes to PTSD related marijuana use on Twitter. Methods We collected tweets that contained the “PTSD” and “Post Trauma Stress Disorder” from August 1, 2015 to April 15, 2016 (n = 1,253,872 tweets). A Naïve Bayes model was constructed to classify tweets into two opinion polarities (support vs. neutral/against marijuana use for PTSD). Results The marijuana related tweets were predominated by the supporting opinions (89.6%). The public opinions about marijuana use for PTSD on Twitter were significantly associated with state-level legislation. States that legalized medical and recreational marijuana use had the highest prevalence of support tweets (1.3 ± 0.6), followed by the states that legalized medical but not recreational use (0.5 ± 0.3) and the states that had no laws legalizing marijuana (0.2 ± 0.1, p < 0.0001). A higher prevalence of support tweets was associated with states with a lower proportion of youth (r = −0.35, p = 0.01) and a higher education rate (r = 0.38, p = 0.006). Conclusion Twitter data suggest a proliferation of supporting marijuana use for PTSD treatments, especially in the states that legalized medical and/or recreational use of marijuana.

KW - Marijuana

KW - PTSD

KW - Socio-economic factors

KW - State-level legalization

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=85009151420&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009151420&partnerID=8YFLogxK

U2 - 10.1016/j.chb.2016.12.064

DO - 10.1016/j.chb.2016.12.064

M3 - Article

VL - 70

SP - 282

EP - 290

JO - Computers in Human Behavior

JF - Computers in Human Behavior

SN - 0747-5632

ER -