Evaluating National CMV Awareness Month: Infodemiology study using artificial intelligence methods to analyze content and sentiment of social media posts (Preprint)

BACKGROUND The month of June has been recognized as National 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 infections. Social media is a powerful tool to support public health by making health information easily accessible. With an estimated 5.1 billion users worldwide and an average of ~2.5 hours spent daily per person on these platforms, social media offers an unparalleled opportunity to promote CMV awareness and prevention. OBJECTIVE The purpose of this study was to evaluate social media messaging before, during, and after 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 through 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 generalizable artificial intelligence (AI) methods (Cohen’s Kappa = 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 National CMV Awareness Month. RESULTS CMV-relevant post volume increased 55% during the campaign month and returned to pre-campaign levels in July. Overall, academic/university researchers were the most frequent authors, pediatric populations were 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 (2= 144.3, df=2, P<.001), awareness or prevention messaging (2= 107.8, df=2, P <.001), and post sentiment (2= 163.6, df=4, P <.001). The intended audience of posts shifted toward the general population from scientist/healthcare professionals during the campaign month (Adjusted Pearson’s Residuals, P<.05). Awareness messaging increased in June 2023, particularly in relation to CMV transmission and disease burden while in contrast, prevention messaging decreased (Adjusted Pearson’s Residuals, P<.05). Finally, while posts were generally neutral in sentiment, a significant shift occurred toward positive sentiment during the campaign month (Adjusted Pearson’s Residuals, P<.05), a sentiment that was more likely to engage the user (Kruskal-Wallis; 2 =194.31, df= 2, P<.001). CONCLUSIONS National CMV Awareness Month 2023 shifted the digital CMV conversation toward public-facing messaging and raised awareness efforts. While 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.