Automatic Detection and Prediction of Psychiatric Hospitalizations From Social Media Posts

Zhengping Jiang, Jonathan Zomick, Sarah Ita Levitan, Mark Serper, Julia Hirschberg


Abstract
We address the problem of predicting psychiatric hospitalizations using linguistic features drawn from social media posts. We formulate this novel task and develop an approach to automatically extract time spans of self-reported psychiatric hospitalizations. Using this dataset, we build predictive models of psychiatric hospitalization, comparing feature sets, user vs. post classification, and comparing model performance using a varying time window of posts. Our best model achieves an F1 of .718 using 7 days of posts. Our results suggest that this is a useful framework for collecting hospitalization data, and that social media data can be leveraged to predict acute psychiatric crises before they occur, potentially saving lives and improving outcomes for individuals with mental illness.
Anthology ID:
2021.clpsych-1.14
Volume:
Proceedings of the Seventh Workshop on Computational Linguistics and Clinical Psychology: Improving Access
Month:
June
Year:
2021
Address:
Online
Editors:
Nazli Goharian, Philip Resnik, Andrew Yates, Molly Ireland, Kate Niederhoffer, Rebecca Resnik
Venue:
CLPsych
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
116–121
Language:
URL:
https://aclanthology.org/2021.clpsych-1.14
DOI:
10.18653/v1/2021.clpsych-1.14
Bibkey:
Cite (ACL):
Zhengping Jiang, Jonathan Zomick, Sarah Ita Levitan, Mark Serper, and Julia Hirschberg. 2021. Automatic Detection and Prediction of Psychiatric Hospitalizations From Social Media Posts. In Proceedings of the Seventh Workshop on Computational Linguistics and Clinical Psychology: Improving Access, pages 116–121, Online. Association for Computational Linguistics.
Cite (Informal):
Automatic Detection and Prediction of Psychiatric Hospitalizations From Social Media Posts (Jiang et al., CLPsych 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.clpsych-1.14.pdf