MétaCan
Menu
Back to cohort
Record W4410281226 · doi:10.2196/69817

Exploring Mental Health Content Moderation and Well-Being Tools on Social Media Platforms: Walkthrough Analysis

2025· article· en· W4410281226 on OpenAlexvenueno aff
Zoë Haime, Lucy Biddle

Bibliographic record

VenueJMIR Human Factors · 2025
Typearticle
Languageen
FieldComputer Science
TopicHate Speech and Cyberbullying Detection
Canadian institutionsnot available
Fundersnot available
KeywordsPreprintModerationMental healthSoftware walkthroughSocial mediaPsychologyComputer scienceWorld Wide WebSocial psychologyPsychotherapist

Abstract

fetched live from OpenAlex

BACKGROUND: Social networking site (SNS) users may experience mental health difficulties themselves or engage with mental health-related content on these platforms. While SNSs use moderation systems and user tools to limit harmful content availability, concerns persist regarding the implementation and effectiveness of these methods. OBJECTIVE: This study aimed to use an ethnographic walkthrough method to critically evaluate 4 SNSs-Instagram, TikTok, Tumblr, and Tellmi. METHODS: Walkthrough methods were used to identify and analyze mental health content moderation and safety and well-being resources of SNS platforms. We completed systematic checklists for each of the SNS platforms and then used thematic analysis to interpret the data. RESULTS: Findings highlighted both successes and challenges in balancing user safety and content moderation across platforms. While varied mental health resources were available on platforms, several issues emerged, including redundancy of information, broken links, and a lack of non-US-centric resources. In addition, despite the presence of several self-moderation tool options, there was insufficient evidence of user education and testing around these features, potentially limiting their effectiveness. Platforms also faced difficulties addressing harmful mental health content due to unclear language around what was allowed or disallowed. This was especially evident in the management of mental health-related terminology, where the emergence of "algospeak," where users adopt alternative codewords or phrases to avoid having content removed or banned by moderation systems, highlighted how users easily bypass platform censorship. Furthermore, platforms did not detail support for reporters or reportees of mental health-related content, leaving users susceptible. CONCLUSIONS: Our study resulted in the production of preliminary recommendations for platforms regarding potential mental health content moderation and well-being procedures and tools. We also emphasized the need for more inclusive user-centered design, feedback, and research to improve SNS safety and moderation features.

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 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)0.000
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 score0.895
Threshold uncertainty score0.647

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0000.001
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 head0.144
GPT teacher head0.311
Teacher spread0.167 · 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 teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
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

Citations4
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Human FactorsSame topicHate Speech and Cyberbullying DetectionFrench-language works237,207