MétaCan
Menu
Back to cohort
Record W4414510444 · doi:10.1287/isre.2024.1140

Content Moderation with Shadowbanning

2025· article· en· W4414510444 on OpenAlexaff
Afrouz Hojati, Barrie R. Nault

Bibliographic record

VenueInformation Systems Research · 2025
Typearticle
Languageen
FieldComputer Science
TopicHate Speech and Cyberbullying Detection
Canadian institutionsUniversity of Calgary
Fundersnot available
KeywordsModerationUser-generated contentUser engagementContent (measure theory)Social mediaPerceptionContent creationWelfare

Abstract

fetched live from OpenAlex

Social media platforms face increasing pressure to moderate harmful content while preserving user engagement and free expression. We examine shadowbanning—a strategy that hides content without notifying the user—and compare it to traditional content removal. Our results show that if users only moderately believe that shadowbanning occurs, the platform benefits from a larger user base and higher profit, which also leads to greater social welfare than with content removal or no moderation. Shadowbanning allows the platform to reduce users’ exposure to extreme content without deterring content creators, enabling more participation of users across the extremeness spectrum. However, outcomes depend on user beliefs and the accuracy of moderation technology. When users are highly suspicious of shadowbanning or when moderation tools are significantly imperfect, the platform’s incentives—and the societal benefits—decline. These findings offer practical insights for platform designers and regulators: shadowbanning can be effective, but its benefits hinge on how transparently and accurately it is implemented. Policymakers should account for user perceptions and technological capabilities when evaluating or regulating opaque moderation strategies.

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)0.008
metaresearch head score (Gemma)0.056
Version: metacan-v3-hybrid-931329e0061cValidation 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 score0.009
Threshold uncertainty score0.042

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0080.056
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.000
Science and technology studies0.0010.003
Scholarly communication0.0020.004
Open science0.0010.003
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0090.001

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 head0.083
GPT teacher head0.331
Teacher spread0.248 · 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 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 venueInformation Systems ResearchSame topicHate Speech and Cyberbullying DetectionFrench-language works237,207