Social Media and Health

Use of social media platforms and data to disseminate health information and to understand and improve individual and population health behaviors and outcomes.

Machine Learning and Natural Language Processing for Geolocation-Centric Monitoring and Characterization of Opioid-Related Social Media Chatter

Nov. 1, 2019

Abeed Sarker, Graciela Gonzalez-Hernandez, Yucheng Ruan, Jeanmarie Perrone

Abstract [from journal]

Importance: Automatic curation of consumer-generated, opioid-related social media big data may enable real-time monitoring of the opioid epidemic in the United States.

Objective: To develop and validate an automatic text-processing pipeline for geospatial and temporal analysis of opioid-mentioning social media chatter.

Design, Setting, and Participants: This cross-sectional, population-based study was conducted from December 1, 2017, to August 31, 2019, and used more than 3 years of


The Relationship Between Exogenous Exposure to "The Real Cost" Anti-smoking Campaign and Campaign-Targeted Beliefs

Robert C. Hornik, PhD
Sep. 26, 2019

Elissa C. Kranzler, Robert C. Hornik

Abstract [from journal]

Though previous evaluations of "The Real Cost" anti-smoking campaign demonstrate effects on anti-smoking beliefs and behaviors, results rely on self-reported recall as a measure of exposure and are thus open to reverse causation concerns. Exogenous measures of exposure, assessed independently of outcomes, support stronger causal inferences. In this study, we examined the relationship between Target Rating Points (TRPs) for specific ads available over four-week periods and anti-smoking beliefs in a national sample of adolescent nonsmokers and


Estimating the Health-Related Quality of Life of Twitter Users Using Semantic Processing

Aug. 21, 2019

Karthik V. Sarma, Brennan M.R. Spiegel, Mark W. Reid, Shawn Chen, Raina M. Merchant, Emily Seltzer, Corey W. Arnold

Abstract [from journal]

Social media presents a rich opportunity to gather health information with limited intervention through the analysis of completely unstructured and unlabeled microposts. We sought to estimate the health-related quality of life (HRQOL) of Twitter users using automated semantic processing methods. We collected tweets from 878 Twitter users recruited through online solicitation and in-person contact with patients. All participants completed the four-item Centers for Disease Control Healthy Days Questionnaire at the time of enrollment and 30 days later to


Content Analysis of Metaphors About Hypertension and Diabetes on Twitter: Exploratory Mixed-Methods Study

Jan. 23, 2019

Lauren Sinnenberg, Christina Mancheno, Frances K Barg, David A Asch, Christy Lee Rivard, Emma Horst-Martz, Alison Buttenheim, Lyle...


Background: Widespread metaphors contribute to the public’s understanding of health. Prior work has characterized the metaphors used to describe cancer and AIDS. Less is known about the metaphors characterizing cardiovascular disease.

Objective: The objective of our study was to characterize the metaphors that Twitter users employ in discussing hypertension and diabetes.

Methods: We filtered approximately 10 billion tweets for keywords related to diabetes and hypertension. We coded a random...

Protecting Clinical Trial Participants and Study Integrity in the Age of Social Media

Oct. 24, 2018


Social media communication among clinical trial participants has the potential to pose risks to their safety and to trial integrity. The Social Media ADEPT framework may help mitigate that potential by encouraging investigators and patient partners to work together to Assess social media risks, Design studies to minimize those risks, Educate participants, Preempt problems, and Take additional steps as needed, such as intervening when problems arise.