Abstract
BACKGROUND Scientific misinformation remains a major barrier to effective health communication. Bridging the gap between academic research and public understanding requires tools that simplify scientific language and adapt content to diverse audiences. OBJECTIVE This study presents Maria Ciência, a specialized GPT-based assistant for science communication. The tool supports researchers in translating peer-reviewed scientific findings through simple prompts into accessible, ethically appropriate materials tailored for children, the general public, health professionals, and policymakers. METHODS The tool was configured using prompt engineering techniques and guided by curated reference materials on inclusive and non-stigmatizing scientific language. Materials derived from 47 public health articles resulted in 188 outputs, which were assessed by 121 evaluators using four criteria: clarity, level of detail, language suitability, and content quality. RESULTS Globally, mean scores were high: clarity (4.90), language suitability (4.78), content quality (4.72), and level of detail (4.56), on a 5-point scale. Materials for children and the general public consistently achieved the highest ratings across all criteria. CONCLUSIONS A targeted comparison with the base large language model (ChatGPT 4o) demonstrated superior performance of Maria Ciência in contextual stability. Maria Ciência demonstrates the potential of AI-assisted tools to enhance knowledge translation and counter scientific misinformation by producing scalable, audience-specific content.

This publication has 21 references indexed in Scilit: