Risk and strength: determining the impact of area-level racial bias and protective factors on birth outcomes

风险和优势：确定地区种族偏见和保护因素对出生结果的影响

• 批准号: 10840120
• 负责人: Thu Nguyen
• 金额: $ 30.48万
• 依托单位: UNIV OF MARYLAND, COLLEGE PARK
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-02-17 至 2024-12-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10840120
• 关键词: Address; Administrative Supplement; Area; Attitude; Big Data; Birth; Code; Communication; Communications Media; Data; Data Aggregation; Data Science; Data Sources; Detection; Development; Discrimination; Documentation; Ethnic Origin; Excision; Facebook; Funding; Future; Gender; Gender Identity; Geography; Goals; Hate; Health; Health Disparities Research; Hostility; Image; Image Analysis; Individual; Instagram; Interest Group; Investigation; Lesbian Gay Bisexual Transgender Queer; Link; Location; Measures; Methodology; Methods; Minority; Minority Groups; Modeling; Outcome; Performance; Persons; Policies; Policy Maker; Population; Prejudice; Process; Public Health; Public Opinion; Race; Readiness; Reduce health disparities; Research; Research Personnel; Resources; Risk; Sex Orientation; Social Identification; Source; Speech; Text; Time; Training; Twitter; United States National Institutes of Health; Visual; Work; adverse birth outcomes; computer science; data acquisition; data repository; data reuse; data sharing; data sharing networks; data visualization; deep learning; ethnic identity; ethnic minority; gender minority; health disparity; health equity; health inequalities; image processing; improved; machine learning model; multimodal data; multimodality; parent grant; protective factors; racial bias; racial health disparity; racial identity; racial minority; repository; sexual identity; sexual minority; shared repository; social; social group; social influence; social media; temporal measurement; transgender; trend

PROJECT SUMMARY Our parent grant focused on using deep machine learning models to analyze the text of social media data to create area-level measures of racial sentiment and to link them with birth outcomes. We focused solely on race-based biases and did not analyze visual representations of bias. The promising findings from this work open up questions about the generalizability of this approach for investigating additional health disparities across other intersecting identities like gender and sexual orientation. We also seek to develop new AI/ML methods to derive sentiment from image-based content, which is an increasingly common form of communication on social media. The administrative supplement will allow us to advance this AI/ML area by making the data AI/ML ready for image analysis, training multimodal models that incorporate both text and image analysis, and creating valuable resources that will shorten the time and specialized expertise needed to implement machine learning models to investigate the impact of area-level biases on health inequities. We will be sharing our AI/ML-ready social media-derived measures by creating a public geoportal for interactive data visualization and sharing, which will contain repositories of aggregated data that will facilitate the use of this big data source for future applications in health equity research.

项目总结