Jornal Cienc.IA: Uma Plataforma Web para Divulgação Biomédica Multinível com Rastreabilidade da Evidência

• Maryana Costa do Vale UFV
• Julio C. S. Reis UFV

DOI: https://doi.org/10.5753/webmedia_estendido.2026.34890

Resumo

Open Science expands the availability of scientific knowledge, but access to documents alone does not ensure that non-specialist audiences can fully understand their content. This barrier is particularly relevant in health communication, where biomedical texts contain specialized terminology, complex linguistic structures, numerical information, and scientific qualifiers whose alteration may change how the evidence is interpreted. In this context, this work presents Jornal Cienc.IA, a Web platform designed to support the dissemination of health research findings at different levels of textual accessibility. The platform integrates the collection and editorial screening of scientific abstracts, a fixed baseline translation into Portuguese, evidence structuring, language-model-assisted generation, the production of Science Communication and Easy Reading versions, semantic retrieval of supporting passages, and operational auditing of Intellectual Fidelity. The architecture adopts a human-in-the-loop workflow. Automated checks and language models assist in identifying potential issues related to evidential support, coverage, numerical scope, technical terminology, and preservation of uncertainty, while the final publication decision remains under human responsibility. Thus, Jornal Cienc.IA seeks to combine text simplification and evidence traceability within the same editorial workflow, supporting the production of more accessible scientific content without treating fluency or automated metrics as standalone guarantees of factual correctness.

Palavras-chave: science communication, text simplification, plain language, artificial intelligence, biomedical summarization, factual fidelity

Referências

Sandra Maria Aluísio and Caroline Gasperin. 2010. Fostering Digital Inclusion and Accessibility: The PorSimples Project for Simplification of Portuguese Texts. In Proc. of the NAACL HLT.

Fernando Alva-Manchego, Carolina Scarton, and Lucia Specia. 2021. The (Un)Suitability of Automatic Evaluation Metrics for Text Simplification. In Computational Linguistics.

Ação Educativa and Conhecimento Social. 2024. Indicador de Alfabetismo Funcional – Inaf 2024. 11ª edição do Indicador de Alfabetismo Funcional. [link] Acesso em: 10 ago. 2026.

Emily M. Bender, Timnit Gebru, Angelina McMillan-Major, and Shmargaret Shmitchell. 2021. On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?. In Proc. of the ACM FAT.

Nancy D. Berkman, Stacey L. Sheridan, Katrina E. Donahue, David J. Halpern, and Karen Crotty. 2011. Low Health Literacy and Health Outcomes: An Updated Systematic Review. Annals of Internal Medicine 155, 2 (2011), 97–107.

Cindy Brach (Ed.). 2024. AHRQ Health Literacy Universal Precautions Toolkit (3 ed.). Agency for Healthcare Research and Quality, Rockville, MD. AHRQ Publication No. 23-0075.

Biaoyan Fang, Xiang Dai, and Sarvnaz Karimi. 2024. Understanding Faithfulness and Reasoning of Large Language Models on Plain Biomedical Summaries. In Findings of the ACL: EMNLP.

Tomas Goldsack, Carolina Scarton, Matthew Shardlow, and Chenghua Lin. 2024. Overview of the BioLaySumm 2024 Shared Task on the Lay Summarization of Biomedical Research Articles. In Proc. of the Workshop on Biomedical NLP.

Tomas Goldsack, Zhihao Zhang, Chenghua Lin, and Carolina Scarton. 2022. Making Science Simple: Corpora for the Lay Summarisation of Scientific Literature. In Proc. of the EMNLP.

Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023. Survey of Hallucination in Natural Language Generation. Comput. Surveys 55, 12 (2023), 1–38.

Sebastian Joseph et al. 2024. FactPICO: Factuality Evaluation for Plain Language Summarization of Medical Evidence. In Proc. of the Annual Meeting of the ACL.

Philippe Laban, Tobias Schnabel, Paul N. Bennett, and Marti A. Hearst. 2022. SummaC: Re-Visiting NLI-based Models for Inconsistency Detection in Summarization. Transact. of the ACL 10 (2022), 163–177.

Teresa B. F. Martins, Claudete M. Ghiraldelo, Maria das Graças Volpe Nunes, and Osvaldo Novais de Oliveira Junior. 1996. Readability Formulas Applied to Textbooks in Brazilian Portuguese. Technical Report. ICMSC-USP, São Carlos, Brasil. [link]

Philipe Melo, Fabrício Benevenuto, Daniel Kansaon, Vitor Mafra, and Kaio Sá. 2021. Monitor de WhatsApp: Um Sistema para Checagem de Fatos no Combate à Desinformação. In Anais Estendidos do WebMedia. 79–82.

Sewon Min, Kalpesh Krishna, Xinxi Lyu, Mike Lewis, Wen-tau Yih, PangWei Koh, Mohit Iyyer, Luke Zettlemoyer, and Hannaneh Hajishirzi. 2023. FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation. In Proce. of the Conference on EMNLP. 12076–12100.

Xiaoli Nan, Yuan Wang, and Kathryn Thier. 2022. Why do people believe health misinformation and who is at risk? A systematic review of individual differences in susceptibility to health misinformation. Social Science & Medicine 314 (2022), 115398.

Israel Júnior Borges do Nascimento, Ana Beatriz Pizarro, Jussara M. Almeida, Natasha Azzopardi-Muscat, Marcos André Gonçalves, Maria Björklund, and David Novillo-Ortiz. 2022. Infodemics and health misinformation: a systematic review of reviews. Bulletin of the World Health Organization 9 (2022), 544–561.

Nils Reimers and Iryna Gurevych. 2019. Sentence-BERT: Sentence Embeddings Using Siamese BERT-Networks. In Proc. of the EMNLP and the IJCNLP.

Julio C. S. Reis, Philipe Melo, Márcio Silva, and Fabrício Benevenuto. 2024. O Combate à Desinformação nas Plataformas Digitais: Desafios e Oportunidades. In IV Seminário dos Grandes Desafios da Computação no Brasil (SBC). 96–102.

UNESCO. 2021. UNESCO Recommendation on Open Science. [link] Adopted by the UNESCO General Conference on 23 November 2021.