This study leverages approximately 1 billion geo-located tweets from 2 million users to create a pipeline for estimating population mental health levels (depression and anxiety) at high spatiotemporal resolutions (county-weeks). Language-based mental health assessments (LBMHAs) show significantly higher reliability than existing survey measures, demonstrating temporal validity by reflecting increases in depression and anxiety after major societal events. The LBMHAs also exhibit improved external validity, correlating strongly with health and socioeconomic status measures. This approach provides spatiotemporal mental health estimates exceeding the granularity of current population surveys.
Publisher
npj Digital Medicine
Published On
May 02, 2024
Authors
Siddharth Mangalik, Johannes C. Eichstaedt, Salvatore Giorgi, Jihu Mun, Farhan Ahmed, Gilvir Gill, Adithya V. Ganesan, Shashanka Subrahmanya, Nikita Soni, Sean A. P. Clouston, H. Andrew Schwartz
Tags
mental health
depression
anxiety
social media
geo-located tweets
population estimates
language-based assessments
Related Publications
Explore these studies to deepen your understanding of the subject.
