logo
ResearchBunny Logo
Robust language-based mental health assessments in time and space through social media

Psychology

Robust language-based mental health assessments in time and space through social media

S. Mangalik, J. C. Eichstaedt, et al.

This groundbreaking research by Siddharth Mangalik and colleagues utilizes a staggering 1 billion geo-located tweets from 2 million users to revolutionize how we estimate population mental health levels. Through innovative language-based mental health assessments, the study reveals insights into depression and anxiety dynamics following major societal events, providing unprecedented granularity in mental health surveillance.

00:00
00:00
Playback language: English
Abstract
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
Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny