Action Tweets Linked to Reduced County-Level HIV Prevalence in the United States

Online Messages and Structural Determinants

Molly E. Ireland, Qijia Chen, H. Andrew Schwartz, Lyle H. Ungar, Dolores Albarracin

Research output: Contribution to journalArticle

Abstract

HIV is uncommon in most US counties but travels quickly through vulnerable communities when it strikes. Tracking behavior through social media may provide an unobtrusive, naturalistic means of predicting HIV outbreaks and understanding the behavioral and psychological factors that increase communities’ risk. General action goals, or the motivation to engage in cognitive and motor activity, may support protective health behavior (e.g., using condoms) or encourage activity indiscriminately (e.g., risky sex), resulting in mixed health effects. We explored these opposing hypotheses by regressing county-level HIV prevalence on action language (e.g., work, plan) in over 150 million tweets mapped to US counties. Controlling for demographic and structural predictors of HIV, more active language was associated with lower HIV rates. By leveraging language used on social media to improve existing predictive models of geographic variation in HIV, future targeted HIV-prevention interventions may have a better chance of reaching high-risk communities before outbreaks occur.

Original languageEnglish (US)
Pages (from-to)1256-1264
Number of pages9
JournalAIDS and Behavior
Volume20
Issue number6
DOIs
StatePublished - Jun 1 2016

Fingerprint

HIV
Social Media
Language
Disease Outbreaks
Health Behavior
Condoms
Motivation
Motor Activity
Demography
Psychology
Health

Keywords

  • General action goals
  • HIV
  • Health
  • Language
  • Twitter

ASJC Scopus subject areas

  • Social Psychology
  • Public Health, Environmental and Occupational Health
  • Infectious Diseases

Cite this

Action Tweets Linked to Reduced County-Level HIV Prevalence in the United States : Online Messages and Structural Determinants. / Ireland, Molly E.; Chen, Qijia; Schwartz, H. Andrew; Ungar, Lyle H.; Albarracin, Dolores.

In: AIDS and Behavior, Vol. 20, No. 6, 01.06.2016, p. 1256-1264.

Research output: Contribution to journalArticle

Ireland, Molly E. ; Chen, Qijia ; Schwartz, H. Andrew ; Ungar, Lyle H. ; Albarracin, Dolores. / Action Tweets Linked to Reduced County-Level HIV Prevalence in the United States : Online Messages and Structural Determinants. In: AIDS and Behavior. 2016 ; Vol. 20, No. 6. pp. 1256-1264.
@article{3195bdd5683f4ad2a519f50ae798696c,
title = "Action Tweets Linked to Reduced County-Level HIV Prevalence in the United States: Online Messages and Structural Determinants",
abstract = "HIV is uncommon in most US counties but travels quickly through vulnerable communities when it strikes. Tracking behavior through social media may provide an unobtrusive, naturalistic means of predicting HIV outbreaks and understanding the behavioral and psychological factors that increase communities’ risk. General action goals, or the motivation to engage in cognitive and motor activity, may support protective health behavior (e.g., using condoms) or encourage activity indiscriminately (e.g., risky sex), resulting in mixed health effects. We explored these opposing hypotheses by regressing county-level HIV prevalence on action language (e.g., work, plan) in over 150 million tweets mapped to US counties. Controlling for demographic and structural predictors of HIV, more active language was associated with lower HIV rates. By leveraging language used on social media to improve existing predictive models of geographic variation in HIV, future targeted HIV-prevention interventions may have a better chance of reaching high-risk communities before outbreaks occur.",
keywords = "General action goals, HIV, Health, Language, Twitter",
author = "Ireland, {Molly E.} and Qijia Chen and Schwartz, {H. Andrew} and Ungar, {Lyle H.} and Dolores Albarracin",
year = "2016",
month = "6",
day = "1",
doi = "10.1007/s10461-015-1252-2",
language = "English (US)",
volume = "20",
pages = "1256--1264",
journal = "AIDS and Behavior",
issn = "1090-7165",
publisher = "Springer New York",
number = "6",

}

TY - JOUR

T1 - Action Tweets Linked to Reduced County-Level HIV Prevalence in the United States

T2 - Online Messages and Structural Determinants

AU - Ireland, Molly E.

AU - Chen, Qijia

AU - Schwartz, H. Andrew

AU - Ungar, Lyle H.

AU - Albarracin, Dolores

PY - 2016/6/1

Y1 - 2016/6/1

N2 - HIV is uncommon in most US counties but travels quickly through vulnerable communities when it strikes. Tracking behavior through social media may provide an unobtrusive, naturalistic means of predicting HIV outbreaks and understanding the behavioral and psychological factors that increase communities’ risk. General action goals, or the motivation to engage in cognitive and motor activity, may support protective health behavior (e.g., using condoms) or encourage activity indiscriminately (e.g., risky sex), resulting in mixed health effects. We explored these opposing hypotheses by regressing county-level HIV prevalence on action language (e.g., work, plan) in over 150 million tweets mapped to US counties. Controlling for demographic and structural predictors of HIV, more active language was associated with lower HIV rates. By leveraging language used on social media to improve existing predictive models of geographic variation in HIV, future targeted HIV-prevention interventions may have a better chance of reaching high-risk communities before outbreaks occur.

AB - HIV is uncommon in most US counties but travels quickly through vulnerable communities when it strikes. Tracking behavior through social media may provide an unobtrusive, naturalistic means of predicting HIV outbreaks and understanding the behavioral and psychological factors that increase communities’ risk. General action goals, or the motivation to engage in cognitive and motor activity, may support protective health behavior (e.g., using condoms) or encourage activity indiscriminately (e.g., risky sex), resulting in mixed health effects. We explored these opposing hypotheses by regressing county-level HIV prevalence on action language (e.g., work, plan) in over 150 million tweets mapped to US counties. Controlling for demographic and structural predictors of HIV, more active language was associated with lower HIV rates. By leveraging language used on social media to improve existing predictive models of geographic variation in HIV, future targeted HIV-prevention interventions may have a better chance of reaching high-risk communities before outbreaks occur.

KW - General action goals

KW - HIV

KW - Health

KW - Language

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=84949507935&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949507935&partnerID=8YFLogxK

U2 - 10.1007/s10461-015-1252-2

DO - 10.1007/s10461-015-1252-2

M3 - Article

VL - 20

SP - 1256

EP - 1264

JO - AIDS and Behavior

JF - AIDS and Behavior

SN - 1090-7165

IS - 6

ER -