{
  "id": 6765,
  "url": "https://arxiv.org/abs/2605.12510v1",
  "title": "WhatsApp Vaccine Discourse (WhaVax): An Expert-Annotated Dataset and Benchmark for Health Misinformation Detection",
  "summary": "We introduce WhaVax, a new expert-annotated dataset of vaccine-related WhatsApp messages collected from large Brazilian public groups spanning multiple pandemic years. The dataset was constructed through a rigorous, carefully designed pipeline that integrates keyword-based data collection, semantic deduplication to remove near-duplicate content, and a multi-stage annotation protocol conducted by medical specialists. This process produced a high-quality gold-standard corpus, characterized by subs",
  "authors": "Jônatas H. dos Santos, Julio C. S. Reis, Philipe Melo, João F. H. Olivetti, Thales H. Silva, Matheus Gontijo Guimaraes et al.",
  "category": "research",
  "topics": "misinformation,healthcare",
  "orgs": null,
  "regions": "latam",
  "published_at": "2026-03-25T14:54:09.000Z",
  "fetched_at": "2026-07-14T16:32:45.891Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/6765",
  "original_url": "https://arxiv.org/abs/2605.12510v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}