Virtual Reporter: Automation of News Report and Journalistic Data Collection Using LLMs

  • Rafaela Almeida de Souza UFMT
  • Luís Flávio Ferreira Monteiro UFMT
  • Natan Carvalho de Barros Taques UFMT
  • Cristiano Maciel UFMT
  • Renan Vinicius Aranha USP
  • Thiago Meirelles Ventura UFMT

Resumo


Brazilian Higher Education Institutions (HEIs) receive many incomplete news proposals, increasing screening effort. This article presents the Virtual Reporter, an LLM-based workflow for academic communication that supports missing-field detection, similar-news retrieval, and briefing generation for human review. We evaluate four configurations (fixed-form, direct LLM, structured workflow, and Virtual Reporter + LLM/RAG) on a corpus of 10,189 news records, which we consolidate into 8,681 canonical records. Results on 300 incomplete pitches show that the structured workflow achieved perfect factual precision and no detected hallucinations, while the LLM/RAG variant obtained slightly higher completeness (0.3950 vs. 0.3896) at the cost of a 0.0517 hallucination rate. Factuality is automatically estimated, leaving final editing and publication to journalists.

Referências

Bastos, Bárbara L. E.; GONÇALVES, Estael L.; XAVIER, Cleon; VALLE, Pedro Henrique Dias; ARANHA, Renan V.. Uma página, muitas informações: como as universidades federais lidam com diferentes requisitos legais em seus sites?. In:SIMPÓSIO BRASILEIRO DE ENGENHARIA DE SOFTWARE (SBES), 39., 2025, Recife/PE. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2025. p. 748-754. ISSN 2833-0633. DOI: 10.5753/sbes.2025.11364.

Brasil. Decreto nº 10.185, de 20 de dezembro de 2019. Extingue cargos efetivos vagos e que vierem a vagar dos quadros de pessoal da administração pública federal e veda a abertura de concurso público e o provimento de vagas adicionais para os cargos que especifica. Brasília, DF, 2019. Available at: [link]. Accessed on: 31 May 2026.

Cortes, Corinna; VAPNIK, Vladimir. Support-vector networks. Machine Learning, v. 20, p. 273-297, 1995. DOI: 10.1007/BF00994018.

Diakopoulos, Nicholas. Computational News Discovery: Towards Design Considerations for Editorial Orientation Algorithms in Journalism. Digital Journalism, v. 8, n. 7, p. 945-967, 2020. DOI: 10.1080/21670811.2020.1736946.

Diakopoulos, Nicholas; TRIELLI, Daniel; LEE, Grace. Towards Understanding and Supporting Journalistic Practices Using Semi-Automated News Discovery Tools. Proceedings of the ACM on Human-Computer Interaction, v. 5, CSCW2, Article 406, p. 1-30, 2021. DOI: 10.1145/3479550.

Gil, Antonio Carlos. Como elaborar projetos de pesquisa. 6. ed. São Paulo: Atlas, 2019.

Grant, Maria J.; BOOTH, Andrew. A typology of reviews: an analysis of 14 review types and associated methodologies. Health Information & Libraries Journal, v. 26, n. 2, p. 91-108, 2009. DOI: 10.1111/j.1471-1842.2009.00848.x.

Hagar, Nick; SILVER, Ethan; SPENCER, Clare; DIAKOPOULOS, Nicholas. LLM-Assisted News Discovery in High-Volume Information Streams: A Case Study. arXiv preprint arXiv:2509.25491, 2025. Available at: [link]. Accessed on: 31 May 2026.

Järvelin, Kalervo; KEKÄLÄINEN, Jaana. Cumulated gain-based evaluation of IR techniques. ACM Transactions on Information Systems, v. 20, n. 4, p. 422-446, 2002. DOI: 10.1145/582415.582418.

Ji, Ziwei; LEE, Nayeon; FRIESKE, Rita; YU, Tiezheng; SU, Dan; XU, Yan; ISHII, Etsuko; BANG, Yejin; CHEN, Delong; DAI, Wenliang; CHAN, Ho Shu; MADOTTO, Andrea; FUNG, Pascale. Survey of Hallucination in Natural Language Generation. ACM Computing Surveys, v. 55, n. 12, Article 248, p. 1-38, 2023. DOI: 10.1145/3571730.

Lage, Nilson. Estrutura da notícia. 6. ed. São Paulo: Ática, 2008. Lewis, Patrick; PEREZ, Ethan; PIKTUS, Aleksandra; PETRONI, Fabio; KARPUKHIN, Vladimir; GOYAL, Naman; KÜTTLER, Heinrich; LEWIS, Mike; YIH, Wen-tau; ROCKTÄSCHEL, Tim; RIEDEL, Sebastian; KIELA,

Douwe. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In: Advances in Neural Information Processing Systems 33 (NeurIPS 2020), 2020. DOI: doi.org/10.48550/arXiv.2005.11401 Maynez, Joshua; NARAYAN, Shashi; BOHNET, Bernd; MCDONALD, Ryan. On Faithfulness and Factuality in Abstractive Summarization. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, p. 1906-1919, 2020. DOI: 10.18653/v1/2020.acl-main.173.

Mohamed, Aissa Hadj; SANTOS, Frances A.; REIS, Julio Cesar dos. Enhancing LLM Agent Effectiveness via Reflective Multi-Agent System. In: Workshop-Escola de Sistemas de Agentes, seus Ambientes e Aplicações (WESAAC), 19., 2025, Fortaleza/CE. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2025. p. 206-217. DOI: 10.5753/wesaac.2025.37536.

Motger, Quim; FRANCH, Xavier; MARCO, Jordi. Software-Based Dialogue Systems: Survey, Taxonomy, and Challenges. ACM Computing Surveys, v. 55, n. 5, p. 1-42, 2022. DOI: 10.1145/3527450.

Ratner, Alexander; BACH, Stephen H.; EHRENBERG, Henry; FRIES, Jason; WU, Sen; RÉ, Christopher. Snorkel: Rapid Training Data Creation with Weak Supervision. Proceedings of the VLDB Endowment, v. 11, n. 3, p. 269-282, 2017. DOI: 10.14778/3157794.3157797.

Robertson, Stephen; ZARAGOZA, Hugo. The Probabilistic Relevance Framework: BM25 and Beyond. Foundations and Trends in Information Retrieval, v. 3, n. 4, p. 333-389, 2009. DOI: 10.1561/1500000019.

Salton, Gerard; BUCKLEY, Christopher. Term-weighting approaches in automatic text retrieval. Information Processing & Management, v. 24, n. 5, p. 513-523, 1988. DOI: 10.1016/0306-4573(88)90021-0.

Silva, Eryck; SANTOS, Frances A.; THOMPSON, Pedro; REIS, Julio C. dos. LLM-Powered Conversational Multi-Agent Cognitive System for Collaborative Task Solving. In: Workshop-Escola de Sistemas de Agentes, seus Ambientes e Aplicações (WESAAC), 19., 2025, Fortaleza/CE. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2025. p. 59-70. DOI: 10.5753/wesaac.2025.37528.

Traquina, Nelson. Teorias do jornalismo: porque as notícias são como são. 2. ed. Florianópolis: Insular, 2005.

Veerbeek, Joris; Diakopoulos, Nicholas. Using Generative Agents to Create Tip Sheets for Investigative Data Reporting. arXiv preprint arXiv:2409.07286, 2024. DOI: 10.48550/arXiv.2409.07286.

Wieringa, Roel J. Design Science Methodology for Information Systems and Software Engineering. Berlin, Heidelberg: Springer, 2014. DOI: 10.1007/978-3-662-43839-8.
Publicado
19/10/2026
SOUZA, Rafaela Almeida de; MONTEIRO, Luís Flávio Ferreira; TAQUES, Natan Carvalho de Barros; MACIEL, Cristiano; ARANHA, Renan Vinicius; VENTURA, Thiago Meirelles. Virtual Reporter: Automation of News Report and Journalistic Data Collection Using LLMs. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 23. , 2026, Cuiabá/MT. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2026 . p. 1448-1459. ISSN 2763-9061. DOI: https://doi.org/10.5753/eniac.2026.31124.

Artigos mais lidos do(s) mesmo(s) autor(es)

1 2 3 4 5 6 7 > >>