How Health Care Workers Wield Influence Through Twitter Hashtags: Retrospective Cross-sectional Study of the Gun Violence and COVID-19 Public Health Crises
Bibliographic record
Abstract
BACKGROUND: Twitter has emerged as a novel way for physicians to share ideas and advocate for policy change. #ThisIsOurLane (firearm injury) and #GetUsPPE (COVID-19) are examples of nationwide health care-led Twitter campaigns that went viral. Health care-initiated Twitter hashtags regarding major public health topics have gained national attention, but their content has not been systematically examined. OBJECTIVE: We hypothesized that Twitter discourse on two epidemics (firearm injury and COVID-19) would differ between tweets with health care-initiated hashtags (#ThisIsOurLane and #GetUsPPE) versus those with non-health care-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 the content of tweets; and (2) a closed-vocabulary feature for psycholinguistic categorization among case and comparator tweets. In accordance with conventional linguistic analysis, we used a P<.001, after adjusting for multiple comparisons using the Bonferroni correction, to identify potentially meaningful correlations between language features and outcomes. RESULTS: In total, 67% (n=4828) of #ThisIsOurLane tweets and 36.6% (n=7907) of #GetUsPPE tweets were authored by health care professionals, compared to 16% (n=1152) of #GunViolence and 9.8% (n=2117) of #COVID19 tweets. Tweets using #ThisIsOurLane and #GetUsPPE were more likely to contain health care-specific language; more language denoting positive emotions, affiliation, and group identity; and more action-oriented content compared to tweets with #GunViolence or #COVID19, respectively. CONCLUSIONS: Tweets with health care-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 truthful, actionable messages around public health issues.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.013 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.003 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".