Dataset Information

Experiences with the Twitter Health Surveillance (THS) System.

ABSTRACT: Social media has become an important platform to gauge public opinion on topics related to our daily lives. In practice, processing these posts requires big data analytics tools since the volume of data and the speed of production overwhelm single-server solutions. Building an application to capture and analyze posts from social media can be a challenge simply because it requires combining a set of complex software tools that often times are tricky to configure, tune, and maintain. In many instances, the application ends up being an assorted collection of Java/Scala programs or Python scripts that developers cobble together to generate the data products they need. In this paper, we present the Twitter Health Surveillance (THS) application framework. THS is designed as a platform to allow end-users to monitor a stream of tweets, and process the stream with a combination of built-in functionality and their own user-defined functions. We discuss the architecture of THS, and describe its implementation atop the Apache Hadoop Ecosystem. We also present several lessons learned while developing our current prototype.

SUBMITTER: Rodriguez-Martinez M

PROVIDER: S-EPMC5872152 | biostudies-other | 2017 Jun

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Experiences with the Twitter Health Surveillance (THS) System.

Rodríguez-Martínez Manuel M

Proceedings. IEEE International Congress on Big Data 20170601

Social media has become an important platform to gauge public opinion on topics related to our daily lives. In practice, processing these posts requires big data analytics tools since the volume of data and the speed of production overwhelm single-server solutions. Building an application to capture and analyze posts from social media can be a challenge simply because it requires combining a set of complex software tools that often times are tricky to configure, tune, and maintain. In many insta ...[more]

PMID: 29607412

Similar Datasets

Project description:INTRODUCTION:Adverse childhood experiences (ACEs) are negative life events occurring before the age of 18 y. ACEs are risk factors for heart disease and diabetes in adult life. Furthermore, individuals who experience ACEs are more likely to smoke and become obese-factors associated with poor oral health. OBJECTIVE:This study investigated likely associations between ACEs and the oral health measures of the 2010 Behavioral Risk Factor Surveillance System (BRFSS). METHODS:Data from 16,354 participants of the 2010 BRFSS were analyzed with SAS 9.4. ACE scores were calculated in 2 domains: abuse (emotional, physical, or sexual) and household challenges (parental separation or divorce, intimate partner violence, household substance abuse, household mental illness, and incarceration). ACE scores, ranging from 0 to 8, were categorized into 0, 1, 2, 3, and ≥4. The 2010 BRFSS oral health measures included >1 y since last dental visit, ≥6 teeth extracted, and ≥2 y since last dental cleaning. Survey logistic regression estimated prevalence odds ratios and 95% CIs, adjusted for age, sex, race/ethnicity, and educational attainment. RESULTS:The weighted mean ACE score was 1.74 (95% CI = 1.68 to 1.81), and the weighted and age-standardized percentages of study participants with ACE scores of 0, 1, 2, 3, and ≥4 were 33.1%, 24.3%, 14.9%, 9.69%, and 18.1%, respectively. There appeared to be a dose-response association between categories of ACE scores and the oral health measures. Specifically, when compared with participants with an ACE score of 0, participants with ACE scores of 1, 2, 3, and ≥4 had adjusted prevalence odds ratios (95% CIs) of 1.10 (0.82 to 1.47), 1.20 (0.90 to 1.60), 1.35 (0.98 to 1.85), and 1.72 (1.31 to 2.26), respectively, for reporting ≥2 y since last dental cleaning. CONCLUSIONS:Findings suggest that ACEs may be associated with poor oral health measures in adulthood, even after adjusting for important oral diseases risk factors. Longitudinal follow-up studies are needed to delineate pathways by which this relationship occurs. KNOWLEDGE TRANSFER STATEMENT:Our findings indicate that exposure to childhood trauma may have negative impacts on oral health in adulthood. Oral health practitioners need to be aware of the potential impacts of childhood trauma on health behaviors that ultimately affect oral health outcomes.

Project description:IntroductionA holistic public health surveillance approach can help capture the public's tobacco and marijuana-related attitudes and behaviors. Using publicly available data from Twitter, this is one of the first studies to describe key topics of discussions related to each intersection (e-cigarette, combustible tobacco, and marijuana) of the Triangulum framework.Aims and methodsTwitter posts (n = 999 447) containing marijuana, e-cigarette, and combustible tobacco terms were collected from January 1, 2018 to December 23, 2019. Posts to Twitter with co-occurring mentions of keywords associated with the Triangulum were defined as an intersection (e-cigarettes and combustible tobacco, combustible tobacco and marijuana, e-cigarettes and marijuana, and marijuana, e-cigarettes and combustible tobacco). Text classifiers and unsupervised machine learning were used to identify predominant topics in posts.ResultsProduct Features and Cartridges were commonly referenced at the intersection of e-cigarette and marijuana-related conversations. Blunts and Cigars and Drugs and Alcohol were commonly referenced at the intersection of combustible tobacco and marijuana-related discussions. Flavors and Health Risks were discussed at the intersection of e-cigarette and combustible-related conversations, while discussions about Illicit products and Health risks were key topics of discussion when e-cigarettes, combustible tobacco, and marijuana were referenced all together in a single post.ConclusionBy examining intersections of marijuana and tobacco products, this study offers inputs for designing comprehensive FDA regulations including regulating product features associated with appeal, improving enforcement to curb sales of illicit products, and informing the FDA's product review and standards procedures for tobacco products that can be used with marijuana.ImplicationsThis study is the first to leverage the Triangulum framework and Twitter data to describe key topics of discussions at the intersection of e-cigarette, combustible tobacco, and marijuana. Real-time health communication interventions can identify Twitter users posting in the context of e-cigarettes, combustible tobacco, and marijuana by automated methods and deliver tailored messages. This study also demonstrates the utility of Twitter data for surveillance of complex and evolving health behaviors.

Project description:BackgroundTo date Health information (HI) in the European Union does not comprise indicators or other information related to impacts of hazardous chemicals in consumer products, food, drinking water or air on the health status of the population. Therefore, we inventorised and evaluated the potential of environmental health surveillance and research data sources in the European population to provide HBM-based indicators of internal human exposure and health impact of relevant chemicals.MethodsWe established an up-dated inventory of European cross-sectional Human Biomonitoring (HBM) surveys and of birth cohorts, and compared chemicals and chemical groups addressed by HBM with indicators and health end points collected via European Core Health Indicators (ECHI), in birth registries, as well as in environmental and food data bases and health registries to see on how data collection could be aligned. Finally, we investigated study designs of HBM survey and health examination surveys for potential synergies.ResultsThe inventory covers a total of 11 European cross-sectional national programmes and a large number of birth cohorts and includes information on study population, age groups, covered substances, sampled matrices, and frequency. The comparison of data collections shows that there are many overlaps between environmental chemicals with environmental and health reporting. HBM data could be linked with ECHI indicators for work-related risks, body mass index (BMI), and low birth weight, with perinatal disease, neurologic disorders, and some chronic diseases, or with data bases for e.g. indoor air, food, or consumer products. Existing initiatives to link data collections at European Environment Agency (EEA) and Joint Research Center (JRC) or at World Health Organization (WHO) are good options to further develop linkage of HBM with exposures sources and health end points.ConclusionsThere is potential to use HBM based information in a number of public health policies, and this would help to align reporting to international commitments. Environmental health surveillance based on HBM and HBM-based indicators, is an excellent tool to inform public health policies about risks from environmental chemicals, and the EU health information system would benefit from additional HBM-based indicators for monitoring exposure burden from environmental chemicals. Considerable efforts are needed to align and establish routine data collections and to develop a surveillance system and indicators which may inform public health policies.

Dataset Information

Experiences with the Twitter Health Surveillance (THS) System.

Publications

Experiences with the Twitter Health Surveillance (THS) System.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets