In order to join virtual sessions, you must be registered and logged-in(Were you registered for the in-person meeting in Denver? if yes, just log in.) 
Note: All session times are in Mountain Daylight Time.

Linking Geo-tagged social media data with health registries to improve public health studies

Authors: Ping Yin*, University of Mary Washington
Topics: Medical and Health Geography, Spatial Analysis & Modeling
Keywords: Twitter, Birth registry, geocoding, spatio-temporal matching
Session Type: Paper
Presentation File: No File Uploaded


Traditional health surveys are usually expensive and time-consuming, making the acquisition of a large sample difficult and, in turn, resulting in high uncertainty in the study results. This proposed research aims to explore the feasibility of linking two existing data sources– health registries and social media data – mainly based on spatial and temporal information to provide a large sample and rich information for various public health studies. As an example, this proposed research will explore the methods for identifying Geo-tagged twitter tweets of mother users recorded in the birth registries of the state of Georgia. Also, the uncertainty of the results will be evaluated. The study is expected to provide a more economic and efficient way to obtain a large sample including both health and demographic information of individuals recorded in health registries and thoughts, feelings, and activities of individuals exposed in public social media. The resulting sample set could be a valuable data source for a series of health studies that help improve our understanding on the impacts of socioeconomic, psychological, environmental, and behavioral factors on health outcomes and health care utilization.

To access contact information login