JMIR Publications

ABSTRACT

Background:

Large racial and ethnic disparities in birth outcomes persist. Increasing evidence points to the role of racism in creating and perpetuating these disparities. Despite the known biological mechanisms linking racism to birth outcomes, valid measures of area-level racial attitudes and bias enabling these persistent disparities have remained more elusive.

Objective:

We used Twitter data to measure state-level racial sentiments and investigate their associations with preterm and low birth weight.

Methods:

A random 1% sample of publicly available tweets from January 1, 2011 – December 31, 2021 were collected using Twitter’s Academic Application Programming Interface (API) (N=56,400,097). We restricted our analyses to English-language tweets from the United States that used one or more race-related keywords. We assessed the sentiment of each tweet using Support Vector Machine (SVM), a supervised machine learning model. For each year, state-level racial sentiment was merged with data on births during that year. We estimated incidence ratios (IRs) for LBW and preterm births (separately) using log binomial regression models, among all mothers, Black mothers, minoritized mothers (Black, Latinx, or Asian mothers), and White mothers. Models were controlled for individual-level maternal characteristics and state-level demographic characteristics.

Results:

Mothers living in states in the highest tertile of negative racial sentiment for tweets referencing racial and ethnic minoritized groups had 8% higher (95% CI: 3%-13%) incidence of low birth weight and 5% higher (95% CI: 0%-11%) incidence of preterm birth compared to mothers living in the lowest tertile of negative racial sentiment. Negative racial sentiment referencing minoritized groups was associated with birth outcomes in the total population, among minoritized mothers, and among White mothers. When examining racial/ethnic specific sentiment, Black mothers living in states in the highest tertile of negative Black sentiment had 6% (95% CI: 1%-11%) and 7% (95% CI: 2%-13%) higher incidence of low birth weight and preterm birth, respectively compared to mothers living in the lowest tertile. Negative Latinx sentiment was associated with a 6% (95% CI: 1%-11%) and 3% (95% CI: 0%-6%) higher incidence of low birth weight and preterm birth, respectively.

Conclusions:

Negative state-level racial sentiment towards minoritized groups, Blacks, and Latinx expressed in the public forum of Twitter was associated with worse individual birth outcomes.