The Association Between State-Level Racial Attitudes Assessed From Twitter Data and Adverse Birth Outcomes: Observational Study

Abstract

<jats:sec> <jats:title>Background</jats:title> <jats:p>In the United States, racial disparities in birth outcomes persist and have been widening. Interpersonal and structural racism are leading explanations for the continuing racial disparities in birth outcomes, but research to confirm the role of racism and evaluate trends in the impact of racism on health outcomes has been hampered by the challenge of measuring racism. Most research on discrimination relies on self-reported experiences of discrimination, and few studies have examined racial attitudes and bias at the US national level.</jats:p> </jats:sec> <jats:sec> <jats:title>Objective</jats:title> <jats:p>This study aimed to investigate the associations between state-level Twitter-derived sentiments related to racial or ethnic minorities and birth outcomes.</jats:p> </jats:sec> <jats:sec> <jats:title>Methods</jats:title> <jats:p>We utilized Twitter’s Streaming application programming interface to collect 26,027,740 tweets from June 2015 to December 2017, containing at least one race-related term. Sentiment analysis was performed using support vector machine, a supervised machine learning model. We constructed overall indicators of sentiment toward minorities and sentiment toward race-specific groups. For each year, state-level Twitter-derived sentiment data were merged with birth data for that year. The study participants were women who had singleton births with no congenital abnormalities from 2015 to 2017 and for whom data were available on gestational age (n=9,988,030) or birth weight (n=9,985,402). The main outcomes were low birth weight (birth weight ≤2499 g) and preterm birth (gestational age &lt;37 weeks). We estimated the incidence ratios controlling for individual-level maternal characteristics (sociodemographics, prenatal care, and health behaviors) and state-level demographics, using log binomial regression models.</jats:p> </jats:sec> <jats:sec> <jats:title>Results</jats:title> <jats:p>The accuracy for identifying negative sentiments on comparing the machine learning model to manually labeled tweets was 91%. Mothers living in states in the highest tertile for negative sentiment tweets referencing racial or ethnic minorities had greater incidences of low birth weight (8% greater, 95% CI 4%-13%) and preterm birth (8% greater, 95% CI 0%-14%) compared with mothers living in states in the lowest tertile. More negative tweets referencing minorities were associated with adverse birth outcomes in the total population, including non-Hispanic white people and racial or ethnic minorities. In stratified subgroup analyses, more negative tweets referencing specific racial or ethnic minority groups (black people, Middle Eastern people, and Muslims) were associated with poor birth outcomes for black people and minorities.</jats:p> </jats:sec> <jats:sec> <jats:title>Conclusions</jats:title> <jats:p>A negative social context related to race was associated with poor birth outcomes for racial or ethnic minorities, as well as non-Hispanic white people.</jats:p> </jats:sec>

Exploring U.S. Shifts in Anti-Asian Sentiment with the Emergence of COVID-19

“…A rise in negative racial attitudes and racial bias can have significant social, economic, and mental and physical health impacts [ 6 , 7 , 8 ]. Prior research has shown that community-level racial climate is related to birth outcomes [ 9 , 10 , 11 ], cardiovascular outcomes [ 12 ], and mortality [ 13 ] of the area. Such attitudes reflect cultural racism, defined as the infusion of the ideology of racial inferiority in the values, language, imagery, symbols, and unstated assumptions of the larger society [ 14 ].…”

Advances of Sentiment Analysis Applications in Obstetrics/Gynecology and Midwifery

“…However, the need for more extended studies is urgent, as numbers of disparities have been increasing over the years. Nguyen et al ( 27 , 28 ), tried to identify the connection between state-level Twitter-derived sentiments and racial or ethnic disparities in birth outcomes. More specifically, researchers collected 26.027.740 relevant tweets from June 2015 to December 2017 and conducted sentiment analysis using a supervised machine learning model (Support Vector Machine).…”

Evaluating associations between area-level Twitter-expressed negative racial sentiment, hate crimes, and residents' racial prejudice in the United States

“…For example, in a multilevel survival analysis, Lee and colleagues found community-level racial bias was associated with mortality independent of individual-level racial bias ( Lee, Muennig, Kawachi, & Hatzenbuehler, 2015 ). Emerging work has also shown that area-level racial bias is associated with worse health outcomes for both racial/ethnic minorities as well as Whites ( Leitner et al, 2016 ; T.; Nguyen et al, 2020 ; Nguyen et al, 2018 ). Taken together, the growing body of evidence indicates the potential influence of area-level racial bias on the health of communities.…”

“…We performed a sentiment analysis on the Twitter data set. This procedure has been previously described ( Nguyen et al, 2020 ). Briefly, we utilized Support Vector Machines (SVM), a supervised machine learning model to label the tweets.…”

“…Building on prior research, our measure offers new, cost-efficient data sources for characterizing area-level racial sentiment ( Nguyen et al, 2019 ). The measure demonstrated associations with adverse birth outcomes (T. Nguyen et al, 2020 ; Nguyen et al, 2018 ) and cardiovascular outcomes ( Huang, Huang, Adams, Nguyen, & Nguyen, 2020 ).…”