MétaCan
Menu
Back to cohort
Record W4407753658 · doi:10.3233/shti250003

Mining Public Voices: Analyzing Suicide-Related Thoughts and Behaviors in YouTube Videos and Comments Using Topic Modeling

2025· article· en· W4407753658 on OpenAlexaff
Hwayeon Danielle Shin, Iman Kassam, Federica Guccini

Bibliographic record

VenueStudies in health technology and informatics · 2025
Typearticle
Languageen
FieldSocial Sciences
TopicComputational and Text Analysis Methods
Canadian institutionsUniversity of TorontoCentre for Addiction and Mental Health
Fundersnot available
KeywordsSocial mediaInternet privacyPublic opinionPerceptionComputer scienceWorld Wide WebPromotion (chess)Focus (optics)Data scienceFocus groupPsychologySociologyPolitical science

Abstract

fetched live from OpenAlex

YouTube has become a common platform for sharing difficult experiences and sensitive information, including suicide-related thoughts and behaviors. This study analyzes YouTube videos and their comments using topic modeling to explore the common themes discussed within the online community. Our findings show that these videos and comments not only focus on personal stories but also provide encouragement and healthcare-related information, highlighting social media's role in health promotion and peer support. Given that millions of people use various social media platforms to discuss a wide range of topics, these platforms serve as a rich source of data. As such, YouTube videos and comments offer health services researchers a valuable source of public opinion data, providing insights into societal attitudes and perceptions that may differ from those collected through traditional research methods.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.010
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.013
Threshold uncertainty score0.026

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.010
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0050.003
Science and technology studies0.0010.000
Scholarly communication0.0010.002
Open science0.0000.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.140
GPT teacher head0.475
Teacher spread0.336 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueStudies in health technology and informaticsSame topicComputational and Text Analysis MethodsFrench-language works237,207