# Audience-Specific Health Communication: Mixed Methods Evaluation of the Maria Ciência AI-Assisted Knowledge Translation Tool

## TL;DR

Maria Ciência is an AI tool that helps translate scientific research into accessible content for different audiences, improving health communication and reducing misinformation.

## Contribution

Maria Ciência is a novel AI tool designed for science communication, using prompt engineering and inclusive language guidelines to produce audience-specific content.

## Key findings

- Maria Ciência's outputs received high scores in clarity, language suitability, content quality, and level of detail.
- Materials for children and the general public achieved the highest ratings across all criteria.
- Maria Ciência's outputs were more accessible than human-written texts while maintaining high legibility.

## Abstract

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.

This study presents Maria Ciência (LPCT-IGM), 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.

The tool was configured using prompt engineering techniques and guided by curated reference materials on inclusive and nonstigmatizing scientific language. Materials derived from 47 public health papers resulted in 188 outputs, which were assessed by 121 evaluators using 4 criteria: clarity, level of detail, language suitability, and content quality. In addition, outputs generated by Maria Ciência were compared with those produced by a base large language model and with human-written science communication materials. Readability and linguistic accessibility were assessed using multiple established metrics.

Worldwide, 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. A targeted comparison with the base large language model demonstrated superior performance of Maria Ciência in contextual stability. Readability analyses indicated that Maria Ciência’s outputs were significantly more accessible than human-written texts, while maintaining high legibility classifications.

Maria Ciência demonstrates the potential of artificial intelligence–assisted tools to enhance knowledge translation and counter scientific misinformation by producing scalable, audience-specific content that balances accessibility and informational integrity.