MétaCan
Menu
← Back to cohort

AI Monitoring of Social Media to Assist in Crisis Preparedness and Response: COVID-19 Case Study

2025· article· W4417004094 on OpenAlexaff
A. Skumanich, Han Kyul Kim, N. A. Sawyer, Reza Davariar

Bibliographic record

Venuenot available
Typearticle
Language
FieldSocial Sciences
TopicMisinformation and Its Impacts
Canadian institutionsUniversity of British Columbia
Fundersnot available
KeywordsSocial mediaMisinformationPreparednessPublic healthFlexibility (engineering)Health carePublic health surveillanceSocial media analyticsPsychological intervention

Abstract

fetched live from OpenAlex

Social media has emerged as a critical frontier in public health, serving as both an information platform and a vector for the rapid spread of health-related false information. Infodemiology, the science of identifying and mitigating the consequences of infodemics, is increasingly vital for addressing public health challenges. The proliferation of false information, accelerated by Generative AI, poses significant risks, leading to adverse health outcomes, unnecessary suffering, and systemic burdens on health care providers and practitioners. This study presents an AI Agentic-like approach to crisis preparedness and response by leveraging AIIML analytics to develop a Capture/Track/Respond (CTR) framework for detecting and counteracting medical false information in real-time social media streams. Our analysis demonstrates high accuracy in identifying false information, enabling timely detection of developing issues, rapid interventions and reliable implementation of corrective measures. We focus on health crises as a specific concern, but the findings can be broadly generalized to any crisis. Our research question addresses the urgent need for scalable, data-driven tools to bolster global crisis preparedness and response, with a starting focus on emerging health crises. The CTR (Capture-Track-Respond) methodology is a template for an efficient, AI-powered framework for rapid detection and mitigation of false information-a critical capability in emergent scenarios where misinformation undermines public trust and safety. Given the potential for generalizability, CTR applies across diverse crisis types, from health emergencies to climate disruptions, which are typically reflected immediately in social media discourse. The flexibility of the approach enables targeted, culturally adaptive messaging via locally preferred digital channels, positioning CTR as a practical tool for humanitarian outreach. By providing health professionals with tools to engage underserved and marginalized populations in real time, this approach advances both global resiliency and health equity.

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)0.003
metaresearch head score (Gemma)0.013
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 score0.018
Threshold uncertainty score0.036

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0030.013
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0020.002
Science and technology studies0.0030.002
Scholarly communication0.0020.003
Open science0.0020.002
Research integrity0.0030.002
Insufficient payload (model declined to judge)0.0040.001

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 head0.065
GPT teacher head0.446
Teacher spread0.381 · 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

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicMisinformation and Its Impacts→French-language works237,207→