Audience-Specific Health Communication: Mixed Methods Evaluation of the Maria Ciência AI-Assisted Knowledge Translation Tool
JMIR Infodemiology · 2026
DOI: 10.2196/78843 ↗Kurz gefasst
Mixed-Methods-Studie in der Zeitschrift JMIR Infodemiology, 2026. Verfasst von Mariana Araújo-Pereira und 7 weiteren Autor:innen. Beteiligte Einrichtung: Laboratório de Pesquisa Clínica e Translacional, Instituto Gonçalo Moniz, R Waldemar Falcão 121, Salvador, 40296-710, Brazil, 1 7131762022. Hauptthemen laut MEDLINE: Health Communication. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Themen: Evidenzbasierte Pflege
Abstract (Originalsprache)
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 (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.
Methods
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.
Results
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.
Conclusions
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Laboratório de Pesquisa Clínica e Translacional, Instituto Gonçalo Moniz, R Waldemar Falcão 121, Salvador, 40296-710, Brazil, 1 7131762022.
- Universidade Federal da Bahia, Salvador, Brazil.
- Curso de Mestrado de Tecnologias em Saúde, Escola Bahiana de Medicina e Saúde Pública, Salvador, Brazil.
ORCID-Profile: Mariana Araújo-Pereira, Klauss Villalva-Serra, Gustavo Pires-Ramos, Beatriz Sousa-Peres, Joanã Nascimento Conceição-Oliveira, Sarah Dourado Maiche, Rebeca Rebouças da Cunha Silva, Bruno de Bezerril Andrade
Zitieren
APA
Araújo-Pereira, M., Villalva-Serra, K., Pires-Ramos, G., Sousa-Peres, B., Conceição-Oliveira, J. N., Maiche, S. D., Silva, R. R. D. C., & Andrade, B. B. (2026). Audience-Specific Health Communication: Mixed Methods Evaluation of the Maria Ciência AI-Assisted Knowledge Translation Tool. JMIR Infodemiology. https://doi.org/10.2196/78843
Vancouver
Araújo-Pereira M, Villalva-Serra K, Pires-Ramos G, Sousa-Peres B, Conceição-Oliveira JN, Maiche SD, et al. Audience-Specific Health Communication: Mixed Methods Evaluation of the Maria Ciência AI-Assisted Knowledge Translation Tool. JMIR Infodemiology. 2026. doi:10.2196/78843
BibTeX
@article{ArajoPereira2026,
author = {Araújo-Pereira, Mariana and Villalva-Serra, Klauss and Pires-Ramos, Gustavo and Sousa-Peres, Beatriz and Conceição-Oliveira, Joanã Nascimento and Maiche, Sarah Dourado and Silva, Rebeca Rebouças da Cunha and Andrade, Bruno de Bezerril},
title = {Audience-Specific Health Communication: Mixed Methods Evaluation of the Maria Ciência AI-Assisted Knowledge Translation Tool},
journal = {JMIR Infodemiology},
year = {2026},
doi = {10.2196/78843}
}
EUVIMED