Interpretable machine learning‐based approaches for understanding suicide risk and protective factors among South Korean females using survey and social media data
Suicide and Life-Threatening Behavior · 2023-06 · 53 (3) · 484-498
DOI: 10.1111/sltb.12959 ↗Kurz gefasst
Fachartikel in der Zeitschrift Suicide and Life-Threatening Behavior, online erschienen am 22.03.2023. Verfasst von Donghun Kim und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Library and Information Science, Yonsei University, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Social Media, Suicide. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: Ministry of Education, National Research Foundation of Korea.
Abstract (Originalsprache)
Objective
We aimed to identify and understand risk and protective factors for suicide among South Korean females by linking survey and social media data and using interpretable machine learning approaches. Materials and Methods We collected a wide range of potential factors including the material, psychosocial, and behavioral data from a detailed survey, which we then linked to data from social media. In addition, we adopted interpretable machine learning approaches to (1) predict the suicide risk, (2) explain the relative importance of factors and their interactions regarding suicide, and (3) understand individual differences affecting suicide risk.
Results
The best‐performing machine learning model achieved an AUC of 0.737. Adverse childhood experiences, social connectedness, and mean positive sentiment score of social media posts were the three risk factors that had a monotonic or unimodal relationship with suicide, and satisfaction with life, narcissistic self‐presentation, and number of close friends on social media were the three protective factors that had a monotonic or unimodal relationship with suicide. We also found several meaningful interactions between specific psychiatric symptoms and narcissistic self‐presentation.
Conclusions
Our findings can help governmental organizations to better assess female suicide risk in South Korea and develop more informed and customized suicide prevention strategies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Library and Information Science, Yonsei University, Seoul, Republic of Korea.
- Department of Media and Communication, Sungkyunkwan University, Seoul, Republic of Korea.
- Department of Social Welfare, Sungkyunkwan University, Seoul, Republic of Korea.
- Division of Child and Adolescent Psychiatry, Department of Psychiatry, Seoul National University Hospital, Seoul, Republic of Korea.
ORCID-Profile: Donghun Kim, Yongjun Zhu
Förderung
- Ministry of Education
- National Research Foundation of Korea
Zitieren
APA
Kim, D., Quan, L., Seo, M., Kim, K., Kim, J. W., & Zhu, Y. (2023). Interpretable machine learning‐based approaches for understanding suicide risk and protective factors among South Korean females using survey and social media data. Suicide and Life-Threatening Behavior, 53(3), 484-498. https://doi.org/10.1111/sltb.12959
Vancouver
Kim D, Quan L, Seo M, Kim K, Kim JW, Zhu Y. Interpretable machine learning‐based approaches for understanding suicide risk and protective factors among South Korean females using survey and social media data. Suicide and Life-Threatening Behavior. 2023;53(3):484-498. doi:10.1111/sltb.12959
BibTeX
@article{Kim2023,
author = {Kim, Donghun and Quan, Lihong and Seo, Mihye and Kim, Kihyun and Kim, Jae-Won and Zhu, Yongjun},
title = {Interpretable machine learning‐based approaches for understanding suicide risk and protective factors among South Korean females using survey and social media data},
journal = {Suicide and Life-Threatening Behavior},
year = {2023},
volume = {53},
number = {3},
pages = {484--498},
doi = {10.1111/sltb.12959}
}
EUVIMED