A comparative study on the credibility of ischemic stroke treatment information on social media platforms: evidence from Weibo and REDnote.

BACKGROUND: Social media is a key channel for public health information, but its open nature leads to mixed quality of information regarding Ischemic Stroke (IS) treatment, which may mislead patient decisions. This study aimed to systematically compare IS treatment information published by professional and lay sources on two major Chinese social media platforms, Weibo and REDnote, in terms of content, engagement, and quality. METHODS: This study employed computational social science and Natural Language Processing (NLP) techniques to analyze posts from four sources (Weibo-Pro, Weibo-Lay, REDnote-Pro, REDnote-Lay). We used topic modeling and co-occurrence networks to analyze content features and developed an automated scoring system based on a Large Language Model (LLM) to quantitatively evaluate information quality on two dimensions: "linguistic features" and "evidence-based medical content". RESULTS: Lay-sourced content exceeded professional-sourced content in both volume and user engagement. Content and quality patterns differed across the two platforms: on Weibo, the evidence-based quality of professional content was significantly higher than that of lay content (p < 0.001), whereas no significant professional-lay difference was detected on REDnote. We refer to this observed convergence as a "quality paradox," while recognizing that the cross-sectional design does not establish a platform effect. Content themes also differed: Weibo-Lay content centered on Traditional Chinese Medicine, whereas REDnote-Lay content focused on rehabilitation experiences and family support. CONCLUSION: Distinct platform- and source-related patterns were observed across four "discursive communities." On REDnote, professional- and lay-sourced posts showed similar evidence-based quality in this sample. These findings support further investigation of platform-specific communication environments and may inform cautious, context-sensitive approaches for patients, clinicians, and platform managers.