JMIR Publications

ABSTRACT

Background:

Stillbirth, the loss of a fetus after the 20th week of pregnancy, affects about 1 in 160 deliveries in the U.S. and nearly 1 in 70 globally. It takes a deep emotional toll on parents, often resulting in grief, depression, anxiety, and post-traumatic stress disorder (PTSD), exacerbated by societal stigma and a lack of public awareness. Despite this, no comprehensive analysis has explored the full range of social media discussions surrounding stillbirth.

Objective:

This study aimed to analyze stillbirth-related content on Instagram and X by (1) identifying dominant themes using topic modeling, evaluated using Latent Dirichlet Allocation (LDA), Non-Negative Matrix Factorization (NMF), and BERTopic; (2) detecting influential hashtags via co-occurrence network analysis; (3) examining sentiments and emotions using transformer-based models; (4) categorizing visual representations of stillbirth on Instagram through manual image analysis with a predefined codebook; and (5) screening for misinformation relating to stillbirth on X.

Methods:

Stillbirth-related posts were collected from Instagram (#stillbirth: N=7,415; #stillbirthawareness: N=8,312; 2023–2024) and X (#stillbirth: N=11,668; 2020–2024) using RapidAPI. Our comparative analyses were limited to 2023–2024. Hashtag co-occurrence networks were analyzed using the PageRank algorithm. Topic modeling was evaluated using LDA, NMF, and BERTopic, with coherence scores guiding our model selection. Sentiment and emotion analyses were carried out using transformer-based RoBERTa and DistilRoBERTa. Misinformation screening was applied to X posts. On Instagram, two representative image samples (n=366) were manually categorized using a predefined codebook, with the inter-rater reliability being assessed using Cohen’s Kappa.

Results:

Health-related hashtags (e.g., #COVID19) appeared more frequently on X. Topic modeling showed that NMF achieved the highest coherence scores (#stillbirthawareness = 0.624 and #stillbirth = 0.846 on Instagram, #stillbirth = 0.816 on X). Medical misinformation appeared in 27.8% (149/536) of tweets linking COVID-19 vaccines to stillbirth. In the image analysis, “Image of text” was most common, followed by remembrance visuals (e.g., gravesites, stillborn infants). The inter-rater reliability was strong—κ=0.837 (95% CI 0.773–0.891) and κ=0.821 (95% CI 0.755–0.879)—with high category correlation (r=0.999; P<.001) and no significant difference (χ²=12.37; P=.089). The sentiment analysis found that positive sentiments exceeded negative sentiments. The emotion analysis showed that fear and sadness were dominant, with fear being more prevalent on X.

Conclusions:

Instagram emphasizes emotional expression, while X focuses on public health and informational content. Evidence-based communication is necessary to counter misinformation, especially on X, whose real-time affordances amplify fear-based narratives during crises such as COVID-19. Additionally, Instagram’s visual and commemorative content offers an opportunity to legitimize parental grief and to validate and humanize loss by directly involving bereaved parents in awareness campaigns. Platform-specific strategies and stronger moderation could improve the credibility of health discourses. Future research should examine targeted approaches to counter misinformation and assist affected populations.