ECHOExploratory Compendium of Humanity Online

EDTT: Pro-Eating Disorder TikTok Dataset

AnalyzedSmalltextTikTokContent moderationHate speechHealthMental health

A TikTok (pro-eating disorder content) dataset of 85 videos and photo posts annotated using the EDE clinical framework, collected by Shaveet, Viranda, and Choudhury at Cornell University. Each record contains content type (video/photos), human-written content summary, EDE subscale and diagnostic item annotations, visual and audio element labels, audio tempo/valence/arousal scores, harmonic ratio, and mode. EDTT is the first clinically-grounded dataset of pro-eating-disorder TikTok content, with 47 videos and 38 photo posts annotated using the Eating Disorder Examination framework by Cornell researchers. Suitable for eating disorder content detection, harmful content moderation, multimodal annotation research, TikTok platform analysis, clinical NLP, audio-visual content analysis.

#Audio feature#Clinical annotation#Eating disorder#Pro eating disorder

Cite this dataset at edtt.echo.directory

Download data BibTeX JSONSimilar datasets

Analytics

Content metrics

85 records scored · min–maxmean ± 0.675 σ (the interquartile range if the values are roughly normal)mean

audio valenceμ 0.59 ± 0.259
min 0.09max 0.836
low 33%medium 34%high 33%
audio arousalμ 0.342 ± 0.059
min 0.205max 0.497
low 33%medium 34%high 33%
audio tempoμ 126.039 ± 20.429
min 78.3max 172.27
harmonic ratioμ 0.742 ± 0.184
min 0.05max 0.993
low 33%medium 34%high 33%
is video55.3% true
true 55.3%false 44.7%
is major key70.6% true
true 70.6%false 29.4%
21.4
Flesch–Kincaid grade
US school grade level
24.0
Automated readability index
Frequent terms
weighteatingscreentextbodyfoodshapeconcernaudioimageryrestraintselfsnippetrelatedpreoccupationphotocheckingimportancelanguageperformancegirlmediadisclosurecaloriesreadsmemesscenarioexpressionmetricsdietaryrulesemphasisexposedslideaspirationaleatemphasizedfearspokencelebritysummariescontrollipsyncingrecallstomachfoodslosingreadingwomanadolescent

Computed over the full corpus.

Record

Catalog key
edtt
Authors
Eden Shaveet; Viranda, Thalia; Choudhury, Tanzeem
Year
2026
Source paper
EDTT Dataset
DOI / arXiv
10.5281/zenodo.19749827
License
CC BY 4.0 (CC-BY-4.0)
Records
85
Languages
en
Collected
2026 (2020s)
Region
Global (inferred: the platform is used worldwide)

Provenance

Originally published at
https://zenodo.org/records/19749827 link checked
Hosted copy
Mirrored on echo.directory on 2026-10-02, 61.9 KB across 1 files. Checksums in MANIFEST.json.

How to cite

BibTeX

@misc{echo2026,
  title  = {ECHO: Exploratory Compendium of Humanity Online},
  author = {Switzer, Braden and Zafarani, Reza},
  year   = {2026},
  url    = {https://echo.directory},
  note   = {Syracuse University}
}

@misc{https://doi.org/10.5281/zenodo.19749827,
  doi       = {10.5281/ZENODO.19749827},
  url       = {https://zenodo.org/doi/10.5281/zenodo.19749827},
  author    = {Eden Shaveet, and Viranda, Thalia and Choudhury, Tanzeem},
  title     = {EDTT Dataset},
  publisher = {Zenodo},
  year      = {2026},
  copyright = {Creative Commons Attribution 4.0 International}
}

APA

Switzer, B., & Zafarani, R. (2026). ECHO: Exploratory Compendium of Humanity Online [Data repository]. Syracuse University. https://echo.directory

Eden Shaveet, Viranda, T., & Choudhury, T. (2026). EDTT: Pro-Eating Disorder TikTok Dataset [Data set]. https://doi.org/10.5281/zenodo.19749827

MLA

Switzer, Braden, and Reza Zafarani. ECHO: Exploratory Compendium of Humanity Online. Syracuse University, 2026, echo.directory.

Eden Shaveet, et al. EDTT: Pro-Eating Disorder TikTok Dataset. 2026, doi.org/10.5281/zenodo.19749827.

BibTeX · RIS · CSL-JSON

Similar datasets 10 all with scores →