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 OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.794
Threshold uncertainty score0.538

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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