Natural language processing analysis of the psychosocial stressors of mental health disorders during the pandemic

RAVEAU MORALES, MARÍA PAZ; Julián I. Goñi; José F. Rodríguez; Isidora Paiva-Mack; Fernanda Barriga; María P. Hermosilla; Claudio Fuentes-Bravo; Susana Eyheramendy

doi:10.1038/s44184-023-00039-6

Natural language processing analysis of the psychosocial stressors of mental health disorders during the pandemic

Journal

npj Mental Health Research

ISSN

2731-4251

Date Issued

2023-10-05

Author(s)

RAVEAU MORALES, MARÍA PAZ

Faro

Julián I. Goñi

José F. Rodríguez

Isidora Paiva-Mack

Fernanda Barriga

María P. Hermosilla

Claudio Fuentes-Bravo

Susana Eyheramendy

Type

journal-article

DOI

10.1038/s44184-023-00039-6

URL

https://investigadores.udd.cl/handle/123456789/11102

Abstract

Abstract Over the past few years, the COVID-19 pandemic has exerted various impacts on the world, notably concerning mental health. Nevertheless, the precise influence of psychosocial stressors on this mental health crisis remains largely unexplored. In this study, we employ natural language processing to examine chat text from a mental health helpline. The data was obtained from a chat helpline called Safe Hour from the “It Gets Better” project in Chile. This dataset encompass 10,986 conversations between trained professional volunteers from the foundation and platform users from 2018 to 2020. Our analysis shows a significant increase in conversations covering issues of self-image and interpersonal relations, as well as a decrease in performance themes. Also, we observe that conversations involving themes like self-image and emotional crisis played a role in explaining both suicidal behavior and depressive symptoms. However, anxious symptoms can only be explained by emotional crisis themes. These findings shed light on the intricate connections between psychosocial stressors and various mental health aspects in the context of the COVID-19 pandemic.