EUVIMEDDécouvrir EUVIMED
ValidierungsstudieBeobachtungsstudieQuerschnittstudieOpen access

Self-Reported Health Outcomes in Metabolic Health YouTube Comments: Cross-Sectional Study and Rule-Based Natural Language Processing Framework Development and Validation

Ricardo Ribeiro iD, Aneesh Zutshi iD

Journal of Medical Internet Research · 2026-05-26 · 28 · e94855

DOI: 10.2196/94855 ↗

At a glance

Validierungsstudie in Journal of Medical Internet Research, published online on 2026-05-26. Written by Ricardo Ribeiro and 1 co-authors. Institution: Department of Mechanical and Industrial Engineering, NOVA School of Science and Technology, Universidade Nova de Lisboa, Caparica, Lisbon, Portugal. Major MEDLINE topics: Natural Language Processing, Social Media, Self Report. 73 references. The full text is freely available in PubMed Central.

RésuméSubjectsRéférences bibliographiquesCiteRelated studies

Abstract (original language)

Background

YouTube is increasingly used for healthcasting, the sharing of evidence-based dietary and lifestyle interventions by domain experts. In the metabolic health domain, channels focused on therapeutic carbohydrate restriction have accumulated audiences of millions. A distinctive feature is the comment section, where viewers share first-person accounts of health changes, constituting a unique source of real-world outcome data at scale. However, extracting structured health information from unstructured comments presents computational challenges.

Objective

This observational, cross-sectional study aims to develop and validate a precision-optimized computational framework for extracting self-reported health outcomes from healthcasting YouTube comments and to characterize the prevalence, distribution across health aspects, and channel-level variation of reported outcomes across a large-scale metabolic health corpus.

Methods

This study analyzed 43,111 unique YouTube comments from 110 videos across 11 therapeutic carbohydrate restriction-focused healthcasting channels (37,458 unique authors; data span November 2013 to January 2026; collected via YouTube data application programming interface version 3). The methodology comprised 3 construction phases and 5 validation studies. The construction phases were (1) exploratory corpus characterization, (2) iterative development of a 35-aspect hierarchical health outcome ontology, and (3) precision-optimized rule-based classification, validated through precision validation (stratified sample of n=500), recall estimation (n=510), external validation on 5 held-out channels (n=12,653 comments), large language model–assisted interrater reliability assessment, and transformer baseline comparison against Bidirectional Encoder Representations from Transformers (BERT) and Robustly Optimized BERT Pretraining Approach (ROBERTa) classifiers. A supplementary aspect–based sentiment analysis contextualized the positive-only design.

Results

The framework identified 1790 positive health outcome reports (1790/43,111, 4.15% prevalence), achieving 97.6% (488/500) precision (95% CI 95.7%-98.6%) and estimated 56.2% recall (95% CI 43.4%-67.9%). The reports described 6674 positive outcomes, distributed across 35 health aspects and 18 named disease conditions extending beyond weight loss: pain and inflammation reduction (1137/6674, 17%), type 2 diabetes improvement (977/6674, 14.6%), skin health (784/6674, 11.8%), and psychological well-being (731/6674, 11%). Over half (3355/6674, 50.3%) spanned multiple research objectives. Significant channel-level variation was observed (χ²10=927.5; P

Subjects

MeSH terms (MEDLINE)

Natural Language ProcessingSocial MediaSelf ReportCross-Sectional StudiesHumans

Author keywords

YouTubedigital healthhealth outcomeshealthcastingmetabolic healthnatural language processingontology engineeringprecision-optimized extractionself-reported outcomestherapeutic carbohydrate restrictionuser-generated content

Authors and institutions

  • Department of Mechanical and Industrial Engineering, NOVA School of Science and Technology, Universidade Nova de Lisboa, Caparica, Lisbon, Portugal.

ORCID profiles: Ricardo Ribeiro, Aneesh Zutshi

Cite

APA

Ribeiro, R., & Zutshi, A. (2026). Self-Reported Health Outcomes in Metabolic Health YouTube Comments: Cross-Sectional Study and Rule-Based Natural Language Processing Framework Development and Validation. Journal of Medical Internet Research, 28, e94855. https://doi.org/10.2196/94855

Vancouver

Ribeiro R, Zutshi A. Self-Reported Health Outcomes in Metabolic Health YouTube Comments: Cross-Sectional Study and Rule-Based Natural Language Processing Framework Development and Validation. Journal of Medical Internet Research. 2026;28:e94855. doi:10.2196/94855

BibTeX
@article{Ribeiro2026,
  author = {Ribeiro, Ricardo and Zutshi, Aneesh},
  title = {Self-Reported Health Outcomes in Metabolic Health YouTube Comments: Cross-Sectional Study and Rule-Based Natural Language Processing Framework Development and Validation},
  journal = {Journal of Medical Internet Research},
  year = {2026},
  volume = {28},
  pages = {e94855},
  doi = {10.2196/94855}
}
Start for free →