MétaCan
Menu
Back to cohort
Record W4417437964 · doi:10.2196/80922

Using Artificial Intelligence Methods to Evaluate the Effect of the National Cytomegalovirus Awareness Month on the Content and Sentiment of Social Media Posts: Infodemiology Study

2025· article· en· W4417437964 on OpenAlexvenueno aff
Tracy R. Rosebrock, Zhen Yang, Lauren D'Arco, Tarun Birendrakumar Pathak, Rebecca Vislay-Wade, Karen B. Fowler, John Diaz‐Decaro, Colin Kunzweiler

Bibliographic record

VenueJMIR Infodemiology · 2025
Typearticle
Languageen
FieldMedicine
TopicData-Driven Disease Surveillance
Canadian institutionsnot available
Fundersnot available
KeywordsSocial mediaConversationPublic healthCytomegalovirusDigital mediaHealth communication

Abstract

fetched live from OpenAlex

Background The month of June has been recognized as the National Cytomegalovirus (CMV) Awareness Month since 2011 in the United States. Established by government resolution, the goal is to increase awareness and reduce the incidence of congenital CMV infection, a leading cause of preventable birth defects and developmental disabilities. Social media is a powerful tool to support public health by making health information easily accessible. With an estimated 246 million users in the United States and more than half of adults seeking health information through such platforms, social media offers an unparalleled opportunity to promote CMV awareness and prevention. Objective This study aimed to evaluate social media messaging before, during, and after the National CMV Awareness Month to assess how the campaign influenced messaging patterns and sentiment related to specific CMV health topics. Methods Publicly available posts on Twitter/X from May to August 2023 that contained at least one of the five most used CMV-related hashtags were collected using a media monitoring platform. The dataset was preprocessed using a customized Bidirectional Encoder Representations from Transformers tokenizer and a language detection package to remove irrelevant and non-English posts. Validated and artificial intelligence (AI) methods (Cohen κ=0.69) were used to determine the thematic content of posts (N=14,900), such as awareness and prevention messaging, and to characterize the sentiment. Changes in post characteristics were measured in relation to the National CMV Awareness Month. Results CMV-relevant post volume increased by 55% during the campaign month and returned to precampaign levels in July. Overall, academic/university researchers were the most frequent authors, pediatrics was the most frequent population discussed, and vaccines were the most frequently mentioned prevention. Significant associations were observed between the month of post publication and the target audience (χ22=144.3, P<.001), awareness or prevention messaging (χ22=107.8, P<.001), and post sentiment (χ24=163.6, P<.001). The intended audience of posts shifted toward the general population from scientists/health care professionals during the campaign month (adjusted Pearson residuals, P=.009). Awareness messaging increased in June 2023, particularly in relation to CMV transmission and disease burden, while prevention messaging decreased (adjusted Pearson residuals, P=.008). Finally, although posts were generally neutral in sentiment, a significant shift occurred toward a positive sentiment during the campaign month (adjusted Pearson residuals, P=.006), a sentiment that was more likely to engage the user (Kruskal-Wallis; χ22=194.31, P<.001). Conclusions The National CMV Awareness Month in 2023 shifted the digital CMV conversation toward public-facing messaging and raised awareness efforts. Although posts related to CMV prevention generally conveyed a positive sentiment, prevention messaging declined during the campaign. These findings highlight opportunities for future CMV social media initiatives to balance awareness with prevention through evaluation and strategic design using AI models to strengthen CMV public health communication and engagement.

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)0.006
metaresearch head score (Gemma)0.008
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.086
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0060.008
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.000
Science and technology studies0.0000.001
Scholarly communication0.0000.000
Open science0.0000.001
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 head0.176
GPT teacher head0.487
Teacher spread0.310 · 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.

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 venueJMIR InfodemiologySame topicData-Driven Disease SurveillanceFrench-language works237,207