EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Bridging online behavior and clinical insight: A longitudinal LLM-based study of suicidality on YouTube reveals novel digital markers

Ilanit Sobol, Shir Lissak, Refael Tikochinski, Tal Nakash, Anat Brunstein Klomek, Eyal Fruchter, Roi Reichart

Journal of Affective Disorders · 2026-05 · 400 · 121072

DOI: 10.1016/j.jad.2025.121072 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Affective Disorders, 2026-05. Verfasst von Ilanit Sobol und 6 weiteren Autor:innen. Beteiligte Einrichtung: Technion - Israel Institute of Technology, Israel. Electronic address: ilanit1997@gmail.com. Hauptthemen laut MEDLINE: Social Media, Suicide, Attempted, Suicidal Ideation, Suicide. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Suicide remains a leading cause of death in Western countries. As social media becomes central to daily life, digital footprints offer valuable insight into suicidal behavior. Focusing on individuals who attempted suicide while uploading videos to their channels, we investigate: How do linguistic patterns on YouTube reflect suicidal behavior, and how do these patterns align with or differ from expert knowledge? We examined linguistic changes around suicide attempts and compared individuals who attempted suicide while actively uploading to their channel with three control groups: those with prior attempts, those experiencing major life events, and matched individuals from the broader cohort. Applying complementary bottom-up, hybrid, and expert-driven approaches, we analyzed a novel longitudinal dataset of 181 suicide-attempt channels and 134 controls.1 In the bottom-up analysis, LLM-based topic-modeling identified 166 topics; five were linked to suicide attempts, two also showed attempt-related temporal changes (Mental Health Struggles, OR = 1.74; YouTube Engagement, OR = 1.67; p< .01).2 In the hybrid approach, clinical experts reviewed LLM-derived topics and flagged 19 as suicide-related. However, none showed significant effects beyond those identified bottom-up. YouTube Engagement, a platform-specific indicator, was not flagged, underscoring the value of bottom-up discovery. A top-down psychological assessment of suicide narratives revealed differing motivations: individuals describing prior attempts aimed to help others (β = 1.69, p< .01), whereas those attempted during the uploading period emphasized personal recovery (β = 1.08, p< .01). By integrating these approaches, we offer a nuanced understanding of suicidality, bridging digital behavior and clinical insights.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Social MediaSuicide, AttemptedSuicidal IdeationSuicideHumansLarge Language ModelsLongitudinal StudiesFemaleMaleAdultDigital Media

Stichwörter der Autor:innen

Artificial intelligenceLarge language modelSocial mediaSuicideYouTube

Autor:innen und Institutionen

  • Technion - Israel Institute of Technology, Israel. Electronic address: ilanit1997@gmail.com.
  • Technion - Israel Institute of Technology, Israel.
  • Reichman University, Israel.

Zitieren

APA

Sobol, I., Lissak, S., Tikochinski, R., Nakash, T., Brunstein Klomek, A., Fruchter, E., & Reichart, R. (2026). Bridging online behavior and clinical insight: A longitudinal LLM-based study of suicidality on YouTube reveals novel digital markers. Journal of Affective Disorders, 400, 121072. https://doi.org/10.1016/j.jad.2025.121072

Vancouver

Sobol I, Lissak S, Tikochinski R, Nakash T, Brunstein Klomek A, Fruchter E, et al. Bridging online behavior and clinical insight: A longitudinal LLM-based study of suicidality on YouTube reveals novel digital markers. Journal of Affective Disorders. 2026;400:121072. doi:10.1016/j.jad.2025.121072

BibTeX
@article{Sobol2026,
  author = {Sobol, Ilanit and Lissak, Shir and Tikochinski, Refael and Nakash, Tal and Brunstein Klomek, Anat and Fruchter, Eyal and Reichart, Roi},
  title = {Bridging online behavior and clinical insight: A longitudinal LLM-based study of suicidality on YouTube reveals novel digital markers},
  journal = {Journal of Affective Disorders},
  year = {2026},
  volume = {400},
  pages = {121072},
  doi = {10.1016/j.jad.2025.121072}
}
Kostenlos starten →