文章基本信息

标题：Geotagged US Tweets as Predictors of County-Level Health Outcomes, 2015–2016
本地全文：下载
作者：Quynh C. Nguyen , PhD ; Matt McCullough , MNR ; Hsien-wen Meng , MS 等
期刊名称：American journal of public health
印刷版ISSN：0090-0036
出版年度：2017
卷号：107
期号：11
页码：1776-1782
DOI：10.2105/AJPH.2017.303993
语种：English
出版社：American Public Health Association
摘要：Objectives. To leverage geotagged Twitter data to create national indicators of the social environment, with small-area indicators of prevalent sentiment and social modeling of health behaviors, and to test associations with county-level health outcomes, while controlling for demographic characteristics. Methods. We used Twitter’s streaming application programming interface to continuously collect a random 1% subset of publicly available geo-located tweets in the contiguous United States. We collected approximately 80 million geotagged tweets from 603 363 unique Twitter users in a 12-month period (April 2015–March 2016). Results. Across 3135 US counties, Twitter indicators of happiness, food, and physical activity were associated with lower premature mortality, obesity, and physical inactivity. Alcohol-use tweets predicted higher alcohol-use–related mortality. Conclusions. Social media represents a new type of real-time data that may enable public health officials to examine movement of norms, sentiment, and behaviors that may portend emerging issues or outbreaks—thus providing a way to intervene to prevent adverse health events and measure the impact of health interventions. Geography is an important determinant of health. Where we live, including the social, political, economic, and built environment, has an impact on health and creates health inequities. 1–3 County-level contextual factors (e.g., socioeconomic status, public health policy, and access to health care) have been associated with coronary heart disease, 4 health-related quality of life, 5 and obesity. 6 The built environment plays an important role at the county level. For example, density of fast-food restaurants has been associated with higher individual-level weight. 7 Social processes and networks can also affect health through mechanisms such as the maintenance of norms around health behaviors and the stimulation of new interests. However, patterns observed in one area may not be applicable to another as characteristics vary by location. One way to understand disparities is through the use of pervasive and publicly available social media data. The widespread use of the Internet and openly shared personal opinions with geo-tagged check-ins enable researchers to understand real-time local area interactions and perform public health surveillance activities. Twitter is one of the most popular social media platforms in use today. Because of the widespread use of social media, the data can be effectively used to discover patterns and emerging health-related issues. Nascent research has suggested that Web searches and social media can provide up-to-date detection, tracking, and predictions of disease outbreaks. 8 Twitter has been used by researchers and public health agencies to track foodborne illness 9 and for real-time detection of natural disasters and disaster response. 10 Information generated via Twitter can be useful in the examination of various health-related issues, such as sentiment toward a current health topic (e.g., vaccines). 11 Myslín et al. analyzed tweets to examine sentiment toward various tobacco products and found that hookah and electronic cigarettes were characterized by more positive sentiment than references to traditional tobacco products and general references to smoking behavior. 12 Liking or following alcohol marketing social media pages has been found to be associated with early age at first alcohol consumption and heavier alcohol consumption among youths. 13