Accepted for/Published in: JMIR Public Health and Surveillance
Date Submitted: Sep 28, 2020
Date Accepted: Dec 12, 2020
Date Submitted to PubMed: Dec 14, 2020
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
How Healthcare Workers Wield Influence Through Twitter Hashtags: A Tale of Two Public Health Crises
ABSTRACT
Background:
Twitter has emerged as a novel way for physicians to share ideas and advocate for policy change. #ThisIsOurLane and #GetUsPPE are examples of nationwide healthcare-led Twitter campaigns that went viral.
Objective:
Healthcare-initiated Twitter hashtags regarding major public health topics have gained national attention, but their content has not been systematically examined. We aimed to characterize differences between Twitter discourse on two epidemics (firearm injury, and COVID) with the healthcare-initiated hashtags (#ThisIsOurLane and #GetUsPPE) versus those with non-healthcare-initiated hashtags (#gunviolence and #COVID19).
Methods:
Using natural language processing, we compared content, affect, and authorship of a random 1% of tweets using #ThisIsOurLane (Nov 2018-Oct 2019) and #GetUsPPE (March-May 2020), compared to #gunviolence and #COVID19 tweets, respectively. We extracted the relative frequency of single words and phrases and created two sets of features: 1) An open vocabulary feature set to create 50 data-driven-determined word clusters to evaluate content of tweets 2) A closed vocabulary feature for psycholinguistic (tone) categorization among case and comparator tweets.
Results:
Tweets using #ThisIsOurLane and #GetUsPPE were more likely to contain healthcare-specific language than tweets using hashtags #GunViolence and #COVID19. Tweets with #ThisIsOurLane or #GetUsPPE contained more language denoting positive emotions, affiliation, and group identity compared to tweets with #GunViolence or #COVID19, respectively.
Conclusions:
Tweets with healthcare-led hashtags expressed more positivity and more action-oriented language than the comparison hashtags. As social media is increasingly used for news discourse, public education and grassroots organizing, the public health community can take advantage of social media’s broad reach to amplify actionable messages around public health issues. Clinical Trial: n/a
Citation
