Explore the vast range of titles available.

Background The urgency of the COVID-19 pandemic called upon the joint efforts from the scientific and private sectors to work together to track vaccine acceptance and prevention behaviors. Methods Our study utilized individual responses to the Delphi Group at Carnegie Mellon University U.S. COVID-19 Trends and Impact Survey, in partnership with Facebook. We retrieved survey data from January 2021 to February 2022 (n = 13,426,245) to examine contextual and individual-level predictors of COVID-19 vaccine hesitancy, vaccination, and mask wearing in the United States. Adjusted logistic regression models were developed to examine individual and ZIP code predictors of COVID-19 vaccine hesitancy and vaccination status. Given the COVID-19 vaccine was rolled out in phases in the U.S. we conducted analyses stratified by time, January 2021-May 2021 (Time 1) and June 2021-February 2022 (Time 2). Results In January 2021 only 9% of U.S. Facebook respondents reported receiving the COVID-19 vaccine, and 45% were vaccine hesitant. By February 2022, 80% of U.S. Facebook respondents were vaccinated and only 18% were vaccine hesitant. Individuals who were older, held higher educational degrees, worked in white collar jobs, wore a mask most or all the time, and identified as white and Asian had higher COVID-19 vaccination rates and lower vaccine hesitancy across Time 1 and Time 2. Essential workers and blue-collar occupations had lower COVID vaccinations and higher vaccine hesitancy. By Time 2, all adults were eligible for the COVID-19 vaccine, but blacks and multiracial individuals had lower vaccination and higher vaccine hesitancy compared to whites. Those 55 years and older and females had higher odds of wearing masks most or all the time. Protective service, construction, and installation and repair occupations had lower odds of wearing masks. ZIP Code level percentage of the population with a bachelors’ which was associated with mask wearing, higher vaccination, and lower vaccine hesitancy. Conclusion Associations found in earlier phases of the pandemic were generally found to also be present later in the pandemic, indicating stability in inequities. Additionally, inequities in these important outcomes suggests more work is needed to bridge gaps to ensure that the burden of COVID-19 risk does not disproportionately fall upon subgroups of the population.

Anti-Asian hate crimes escalated during the COVID-19 pandemic; however, limited research has explored the association between social media sentiment and hate crimes toward Asian communities. This study aims to investigate the relationship between Twitter (rebranded as X) sentiment data and the occurrence of anti-Asian hate crimes in New York City from 2019 to 2022, a period encompassing both before and during COVID-19 pandemic conditions. We used a hate crime dataset from the New York City Police Department. This dataset included detailed information on the occurrence of anti-Asian hate crimes at the police precinct level from 2019 to 2022. We used Twitter's application programming interface for Academic Research to collect a random 1% sample of publicly available Twitter data in New York State, including New York City, that included 1 or more of the selected Asian-related keywords and applied support vector machine to classify sentiment. We measured sentiment toward the Asian community using the rates of negative and positive sentiment expressed in tweets at the monthly level (N=48). We used negative binomial models to explore the associations between sentiment levels and the number of anti-Asian hate crimes in the same month. We further adjusted our models for confounders such as the unemployment rate and the emergence of the COVID-19 pandemic. As sensitivity analyses, we used distributed lag models to capture 1- to 2-month lag times. A point increase of 1% in negative sentiment rate toward the Asian community in the same month was associated with a 24% increase (incidence rate ratio [IRR] 1.24; 95% CI 1.07-1.44; P=.005) in the number of anti-Asian hate crimes. The association was slightly attenuated after adjusting for unemployment and COVID-19 emergence (ie, after March 2020; P=.008). The positive sentiment toward Asian tweets with a 0-month lag was associated with a 12% decrease (IRR 0.88; 95% CI 0.79-0.97; P=.002) in expected anti-Asian hate crimes in the same month, but the relationship was no longer significant after adjusting for the unemployment rate and the emergence of COVID-19 pandemic (P=.11). A higher negative sentiment level was associated with more hate crimes specifically targeting the Asian community in the same month. The findings highlight the importance of monitoring public sentiment to predict and potentially mitigate hate crimes against Asian individuals.

ObjectiveThe USA has higher rates of fatal motor vehicle collisions than most high-income countries. Previous studies examining the role of the built environment were generally limited to small geographic areas or single cities. This study aims to quantify associations between built environment characteristics and traffic collisions in the USA.MethodsBuilt environment characteristics were derived from Google Street View images and summarised at the census tract level. Fatal traffic collisions were obtained from the 2019–2021 Fatality Analysis Reporting System. Fatal and non-fatal traffic collisions in Washington DC were obtained from the District Department of Transportation. Adjusted Poisson regression models examined whether built environment characteristics are related to motor vehicle collisions in the USA, controlling for census tract sociodemographic characteristics.ResultsCensus tracts in the highest tertile of sidewalks, single-lane roads, streetlights and street greenness had 70%, 50%, 30% and 26% fewer fatal vehicle collisions compared with those in the lowest tertile. Street greenness and single-lane roads were associated with 37% and 38% fewer pedestrian-involved and cyclist-involved fatal collisions. Analyses with fatal and non-fatal collisions in Washington DC found streetlights and stop signs were associated with fewer pedestrians and cyclists-involved vehicle collisions while road construction had an adverse association.ConclusionThis study demonstrates the utility of using data algorithms that can automatically analyse street segments to create indicators of the built environment to enhance understanding of large-scale patterns and inform interventions to decrease road traffic injuries and fatalities.

A major challenge in sentiment analysis on social media is the increasing prevalence of image-based content, which integrates text and visuals to convey nuanced messages. Traditional text-based approaches have been widely used to assess public attitudes and beliefs; however, they often fail to fully capture the meaning of multimodal content where cultural, contextual, and visual elements play a significant role. This study aims to provide practical guidance for collecting, processing, and analyzing social media data using multimodal machine learning models. Specifically, it focuses on training and fine-tuning models to classify sentiment and detect hate speech. Social media data were collected from Facebook and Instagram using CrowdTangle, a public insights tool by Meta, and from X via its academic research application programming interface. The dataset was filtered to include only race-related terms and lesbian, gay, bisexual, transgender, queer, intersex, and asexual community-related posts with image attachments, ensuring focus on multimodal content. Human annotators labeled 13,000 posts into 4 categories: negative sentiment, positive sentiment, hate, or antihate. We evaluated unimodal (Bidirectional Encoder Representations from Transformers for text and Visual Geometry Group 16 for images) and multimodal (Contrastive Language-Image Pretraining [CLIP], Visual Bidirectional Encoder Representations from Transformers [VisualBERTs], and an intermediate fusion) models. To enhance model performance, the synthetic minority oversampling technique was applied to address class imbalances, and latent Dirichlet allocation was used to improve semantic representations. Our findings highlighted key differences in model performance. Among unimodal models, Bidirectional Encoder Representations from Transformer outperformed Visual Geometry Group 16, achieving higher accuracy and macro-F -scores across all tasks. Among multimodal models, CLIP achieved the highest accuracy (0.86) in negative sentiment detection, followed by VisualBERT (0.84). For positive sentiment, VisualBERT outperformed other models with the highest accuracy (0.76). In hate speech detection, the intermediate fusion model demonstrated the highest accuracy (0.91) with a macro-F -score of 0.64, ensuring balanced performance. Meanwhile, VisualBERT performed best in antihate classification, achieving an accuracy of 0.78. Applying latent Dirichlet allocation and the synthetic minority oversampling technique improved minority class detection, particularly for antihate content. Overall, the intermediate fusion model provided the most balanced performance across tasks, while CLIP excelled in accuracy-driven classifications. Although VisualBERT performed well in certain areas, it struggled to maintain a precision-recall balance. These results emphasized the effectiveness of multimodal approaches over unimodal models in analyzing social media sentiment. This study contributes to the growing research on multimodal machine learning by demonstrating how advanced models, data augmentation techniques, and diverse datasets can enhance the analysis of social media content. The findings offer valuable insights for researchers, policy makers, and public health professionals seeking to leverage artificial intelligence for social media monitoring and addressing broader societal challenges.

Large racial and ethnic disparities in adverse birth outcomes persist. Increasing evidence points to the potential role of racism in creating and perpetuating these disparities. Valid measures of area-level racial attitudes and bias remain elusive, but capture an important and underexplored form of racism that may help explain these disparities. Cultural values and attitudes expressed through social media reflect and shape public norms and subsequent behaviors. Few studies have quantified attitudes toward different racial groups using social media with the aim of examining associations with birth outcomes. We used Twitter data to measure state-level racial sentiments and investigate associations with preterm birth (PTB) and low birth weight (LBW) in a multiracial or ethnic sample of mothers in the United States. A random 1% sample of publicly available tweets from January 1, 2011, to December 31, 2021, was collected using Twitter's Academic Application Programming Interface (N=56,400,097). Analyses were on 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, a supervised machine learning model. We used 5-fold cross-validation to assess model performance and achieved high accuracy for negative sentiment classification (91%) and a high F1 score (84%). For each year, the state-level racial sentiment was merged with birth data during that year (~3 million births per year). We estimated incidence ratios for LBW and PTB using log binomial regression models, among all mothers, Black mothers, racially minoritized mothers (Asian, Black, or Latina mothers), and White mothers. Models were controlled for individual-level maternal characteristics and state-level demographics. Mothers living in states in the highest tertile of negative racial sentiment for tweets referencing racial and ethnic minoritized groups had an 8% higher (95% CI 3%-13%) incidence of LBW and 5% higher (95% CI 0%-11%) incidence of PTB compared to mothers living in the lowest tertile. Negative racial sentiment referencing racially minoritized groups was associated with adverse birth outcomes in the total population, among minoritized mothers, and White mothers. 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 LBW and PTB, 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 LBW and PTB among Latina mothers, respectively. Twitter-derived negative state-level racial sentiment toward racially minoritized groups was associated with a higher risk of adverse birth outcomes among the total population and racially minoritized groups. Policies and supports establishing an inclusive environment accepting of all races and cultures may decrease the overall risk of adverse birth outcomes and reduce racial birth outcome disparities.

In recent years, there has been a dramatic increase in the popularity and use of glucagon-like peptide-1 receptor agonists (GLP-1 RAs) for weight loss. As such, it is essential to understand users' real-world discussions of short-term, long-term, and co-occurrent adverse events associated with currently used GLP-1 RA medications. This study aims to quantitatively analyze temporal and co-occurrent GLP-1 RA adverse event trends through discussions of GLP-1 RA weight loss medications on Facebook from 2022 to 2024. We collected 64,202 Facebook posts (59,293 posts after removing duplicate posts) from January 1, 2022, to May 31, 2024, through CrowdTangle, a public insights tool from Meta. Using English language social media posts from the United States, we examined discussions of adverse event mentions for posts referencing 7 GLP-1 RA weight loss product categories (ie, semaglutide, Ozempic, Wegovy, tirzepatide, Mounjaro, Zepbound, and GLP-1 RA as a class). All analyses were conducted using Python (version 3; Python Software Foundation) in a Google Colab environment. Temporal time series analysis revealed that the GLP-1 RAs' adverse event mentions on social media aligned with several key events: the Food and Drug Administration's approval of Wegovy for pediatric weight management in December 2022, increased media coverage in August 2023, celebrity endorsement in December 2023, and Medicare Part D coverage expansion for weight loss medications in March 2024. Gastrointestinal (GI)-related adverse events (general term) were most prevalent for posts mentioning the GLP-1 RA class (210/4885, 4.30%) and Mounjaro (241/4031, 5.98%). In contrast, the most prevalent adverse event mentions noted for tirzepatide were headache (78/4202, 1.86%) and joint pain (71/4202, 1.69%). Hypertension (13/1769, 0.73%) was frequently mentioned in Zepbound posts, while pancreatitis was commonly associated with Mounjaro posts (44/4031, 1.08%), and 2.85% (139/4885) of posts broadly referring to the GLP-1 RA class. Furthermore, an integrated node network analysis revealed 3 distinct GLP-1 RA adverse events-mentioned clusters: cluster 1 (purple) contained allergies, anxiety, depression, chronic obstructive pulmonary disease, fatigue, fever, hypertension, indigestion, insomnia, gastroesophageal reflux disease, hives, swelling, restlessness, and seizures. Cluster 2 (pink) contained constipation, dehydration, headache, diarrhea, dizziness, hypoglycemia, sweating, and jaundice. Cluster 3 (brown) contained GI symptoms, such as nausea, pancreatitis, rash, and vomiting. The GI symptoms, such as nausea, vomiting, pancreatitis, diarrhea, and indigestion, were strongly associated together (≥100 co-occurrence mentions), while the mentioned neurological symptoms, such as anxiety, depression, and insomnia, were highly correlated with each other (50-100 co-occurrence mentions). This social media study highlights the adverse event mention patterns for posts referencing GLP-1 RA medications. While further research is needed to rigorously examine and validate these findings, this study demonstrates the importance of monitoring social media discussions to predict novel, underreported, or rare drug adverse events, thereby improving patient care, clinical research, and health policy interventions.

Social media platforms, such as Facebook, provide a dynamic public space where users of various racial and ethnic backgrounds share content related to identity, politics, and other social issues. These platforms allow racially minoritized groups to both challenge racial silencing and express cultural pride. At the same time, they expose users to racism and stereotypes that can negatively affect their mental and physical health through psychosocial stress. Given the rise of multimodal communication, it is essential to study both images and text to fully understand how race and ethnicity are discussed in digital spaces. This exploratory, descriptive study aimed to investigate how people discuss race and ethnicity on Facebook and specifically examine themes related to cultural pride, solidarity, racism, antiracism, and politics using qualitative content analysis of race- and ethnicity-related Facebook posts with images and text. These themes reflect how individuals construct identity, engage with other social identities, and navigate sociopolitical discourse in digital spaces. We conducted a qualitative content analysis using a hybrid inductive-deductive approach. A total of 500 multimodal Facebook posts were randomly sampled using CrowdTangle, with 100 posts from each year between 2019 and 2023. Each post included both image and text and contained at least 1 race- or ethnicity-related keyword. Posts were uploaded to GitHub for storage and to Label Studio for coding. An iteratively developed codebook guided the analysis, focusing on representations of race and ethnicity, the continuum of race-related discourse, and topical content. All posts were double coded until an 80% interrater agreement was reached. The remaining discrepancies were resolved through coder consensus to ensure reliability and consistency. Themes were solidified through thematic analysis. Across 500 Facebook posts from 2019 to 2023, nearly one-third lacked clear racial specificity, with 19.8% (99/500) unrelated to race and 11.2% (56/500) mentioning no specific racial or ethnic group. Among the identified groups, Hispanic, multiracial, and immigrant communities were the most frequently referenced. Common themes included US politics, cultural pride, racism and stereotypes, and antiracism. Political content was the most crosscutting theme, while cultural pride and racism-related discourse varied by group. Antiracism posts reflected the national response to racial justice movements. These findings highlight the nuanced and evolving nature of race-related discourse on social media. It can be complicated to interpret image-based posts because of the subtle ways in which an image may reference race and ethnicity but does not explicitly mention it, or when there is a contradiction in the ideas portrayed in the image versus the text. Decoding this process on Facebook can help researchers boost the positive impacts and reduce the harmful effects of racism on social media.

Collecting neighborhood data can both be time- and resource-intensive, especially across broad geographies. In this study, we leveraged 1.4 million publicly available Google Street View (GSV) images from Utah to construct indicators of the neighborhood built environment and evaluate their associations with 2017–2019 health outcomes of approximately one-third of the population living in Utah. The use of electronic medical records allows for the assessment of associations between neighborhood characteristics and individual-level health outcomes while controlling for predisposing factors, which distinguishes this study from previous GSV studies that were ecological in nature. Among 938,085 adult patients, we found that individuals living in communities in the highest tertiles of green streets and non-single-family homes have 10–27% lower diabetes, uncontrolled diabetes, hypertension, and obesity, but higher substance use disorders—controlling for age, White race, Hispanic ethnicity, religion, marital status, health insurance, and area deprivation index. Conversely, the presence of visible utility wires overhead was associated with 5–10% more diabetes, uncontrolled diabetes, hypertension, obesity, and substance use disorders. Our study found that non-single-family and green streets were related to a lower prevalence of chronic conditions, while visible utility wires and single-lane roads were connected with a higher burden of chronic conditions. These contextual characteristics can better help healthcare organizations understand the drivers of their patients’ health by further considering patients’ residential environments, which present both risks and resources.

Stark disparities exist in maternal and child outcomes and there is a need to provide timely and accurate health information. In this pilot study, we assessed the feasibility and acceptability of a health chatbot for new mothers of color. Rosie, a question-and-answer chatbot, was developed as a mobile app and is available to answer questions about pregnancy, parenting, and child development. From January 9, 2023, to February 9, 2023, participants were recruited using social media posts and through engagement with community organizations. Inclusion criteria included being aged ≥14 years, being a woman of color, and either being currently pregnant or having given birth within the past 6 months. Participants were randomly assigned to the Rosie treatment group (15/29, 52% received the Rosie app) or control group (14/29, 48% received a children's book each month) for 3 months. Those assigned to the treatment group could ask Rosie questions and receive an immediate response generated from Rosie's knowledgebase. Upon detection of a possible health emergency, Rosie sends emergency resources and relevant hotline information. In addition, a study staff member, who is a clinical social worker, reaches out to the participant within 24 hours to follow up. Preintervention and postintervention tests were completed to qualitatively and quantitatively evaluate Rosie and describe changes across key health outcomes, including postpartum depression and the frequency of emergency room visits. These measurements were used to inform the clinical trial's sample size calculations. Of 41 individuals who were screened and eligible, 31 (76%) enrolled and 29 (71%) were retained in the study. More than 87% (13/15) of Rosie treatment group members reported using Rosie daily (5/15, 33%) or weekly (8/15, 53%) across the 3-month study period. Most users reported that Rosie was easy to use (14/15, 93%) and provided responses quickly (13/15, 87%). The remaining issues identified included crashing of the app (8/15, 53%), and users were not satisfied with some of Rosie's answers (12/15, 80%). Mothers in both the Rosie treatment group and control group experienced a decline in depression scores from pretest to posttest periods, but the decline was statistically significant only among treatment group mothers (P=.008). In addition, a low proportion of treatment group infants had emergency room visits (1/11, 9%) compared with control group members (3/13, 23%). Nonetheless, no between-group differences reached statistical significance at P<.05. Rosie was found to be an acceptable, feasible, and appropriate intervention for ethnic and racial minority pregnant women and mothers of infants owing to the chatbot's ability to provide a personalized, flexible tool to increase the timeliness and accessibility of high-quality health information to individuals during a period of elevated health risks for the mother and child. ClinicalTrials.gov NCT06053515; https://clinicaltrials.gov/study/NCT06053515.

Google Street View (GSV) images offer a unique and scalable alternative to in-person audits for examining neighborhood built environment characteristics. Additionally, most prior neighborhood studies have relied on cross-sectional designs. This study aimed to use GSV images and computer vision to examine longitudinal changes in the built environment, demographic shifts, and health outcomes in Washington, DC, from 2014 to 2019. In total, 434,115 GSV images were systematically sampled at 100 m intervals along primary and secondary road segments. Convolutional neural networks, a type of deep learning algorithm, were used to extract built environment features from images. Census tract summaries of the neighborhood built environment were created. Multilevel mixed-effects linear models with random intercepts for years and census tracts were used to assess associations between built environment changes and health outcomes, adjusting for covariates, including median age, percentage male, percentage Hispanic, percentage African American, percentage college educated, percentage owner-occupied housing, and median household income. Washington, DC, experienced a shift toward higher-density housing, with non-single-family homes rising from 66% to 72% of the housing stock. Single-lane roads increased from 37% to 42%, suggesting a shift toward more sustainable and compact urban forms. Gentrification trends were reflected in a rise in college-educated residents (16%-41%), a US $17,490 increase in the median household income, and a US $159,600 increase in property values. Longitudinal analyses revealed that increased construction activity was associated with lower rates of obesity, diabetes, high cholesterol, and cancer, while growth in non-single-family housing was correlated with reductions in the prevalence of obesity and diabetes. However, neighborhoods with higher proportions of African American residents experienced reduced construction activity. Washington, DC, has experienced significant urban transformation, marked by substantial changes in neighborhood built environments and demographic shifts. Urban development is associated with reduced prevalence of chronic conditions. These findings highlight the complex interplay between urban development, demographic changes, and health, underscoring the need for future research to explore the broader impacts of neighborhood built environment changes on community composition and health outcomes. GSV imagery, along with advances in computer vision, can aid in the acceleration of neighborhood studies.