PreprintArticleVersion 1Preserved in Portico This version is not peer-reviewed
Machine Learning Analysis of Social Media Posts Written in Natural Language May Enhance Suicidal Ideation Detection in Romanian Adults with Major Depression
Version 1
: Received: 17 July 2023 / Approved: 18 July 2023 / Online: 18 July 2023 (07:44:06 CEST)
How to cite:
MD, PhD, E. P. D. Machine Learning Analysis of Social Media Posts Written in Natural Language May Enhance Suicidal Ideation Detection in Romanian Adults with Major Depression. Preprints2023, 2023071177. https://doi.org/10.20944/preprints202307.1177.v1
MD, PhD, E. P. D. Machine Learning Analysis of Social Media Posts Written in Natural Language May Enhance Suicidal Ideation Detection in Romanian Adults with Major Depression. Preprints 2023, 2023071177. https://doi.org/10.20944/preprints202307.1177.v1
MD, PhD, E. P. D. Machine Learning Analysis of Social Media Posts Written in Natural Language May Enhance Suicidal Ideation Detection in Romanian Adults with Major Depression. Preprints2023, 2023071177. https://doi.org/10.20944/preprints202307.1177.v1
APA Style
MD, PhD, E. P. D. (2023). Machine Learning Analysis of Social Media Posts Written in Natural Language May Enhance Suicidal Ideation Detection in Romanian Adults with Major Depression. Preprints. https://doi.org/10.20944/preprints202307.1177.v1
Chicago/Turabian Style
MD, PhD, E. P. D. 2023 "Machine Learning Analysis of Social Media Posts Written in Natural Language May Enhance Suicidal Ideation Detection in Romanian Adults with Major Depression" Preprints. https://doi.org/10.20944/preprints202307.1177.v1
Abstract
Detecting suicidal ideation in adults with major depression is crucial for timely intervention and prevention of self-harm. As suicide is influenced by various biological, socio-cultural and psychological factors, traditional screening methods have accuracy and efficiency limitations. In certain cultures, societal stigma and marginalization can compel individuals with depression to conceal their suffering. Such individuals often turn to online social media platforms and share their experiences with peers under the protection of anonymity. Our research explored the potential of machine learning detection of suicidal ideation among Romanian adults with major depression that contributed to a web-based depression support forum. A trained algorithm (C4.5 decision tree) analyzed 125 posts fed to on a free access online support forum over 5 years (2014 – 2018) and classified them based on suicidal ideation content. 32 texts (25%) were identified as having a high probability of suicidal ideation content. 65% of the authors were male, with a mean age of 36.7±10.3 years and an average duration of illness of 3.4±1.4 years. Texts indicating positive suicidal ideation were generally shorter and elicited more general responses but fewer professional responses compared to those without suicidal ideation content. The study's main limitations include the relatively small number of classified texts, the absence of prospective information and the lack of qualitative evaluation of the excerpts' content. As socio-demographic and linguistic actuarial results were comparable to data reported by real life studies, we may consider basic text mining techniques as a screening tool that is able to detect suicidal ideation in texts written in unstructured Romanian language.
Keywords
Suicidal Ideation, major depression in adults, natural language written texts, Romanian depression support forum, machine learning text mining,
Subject
Medicine and Pharmacology, Psychiatry and Mental Health
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.