Transforming Public Administration: AI-Driven Tools for Summarizing Corruption Cases in Federal Education

• Ruan Rolim Unifesspa
• Giselle Batista Unifesspa
• Pedro Bacelar Unifesspa
• Marcela Souza Unifesspa
• Hugo Kuribayashi Unifesspa

DOI: https://doi.org/10.5753/sbsi_estendido.2025.246815

Resumo

The fight against corruption in public institutions, particularly in universities and federal institutes, requires efficient tools for auditing and monitoring administrative processes. This paper presents a tool designed to analyze corruption cases by identifying key elements within these processes, such as classification, damage, and motivation, while observing recurring patterns. The tool leverages Natural Language Processing (NLP) techniques and Large Language Models (LLMs) to automate the extraction and analysis of relevant information. The results demonstrate that the solution can significantly reduce the time required for audits while enhancing accuracy in detecting irregularities.

Referências

Bai, H. and Chunglun, W. (2024). Mt-sal: Multi-task structure-aware learning for legal document summarization. In 2024 Cross Strait Radio Science and Wireless Technology Conference (CSRSWTC), pages 1–3.

Deroy, A. et al. (2024). Applicability of large language models and generative models for legal case judgement summarization. Artificial Intelligence and Law.

Gilson, D. H. M. I. and Bramili, G. A. (2023). Inteligência artificial no combate à fraude e corrupção: A experiência da controladoria geral do município do rio de janeiro. Revista da CGU [online].

Kanapala, A., Pal, S., and Pamula, R. (2019). Text summarization from legal documents: a survey. Artificial Intelligence Review, 51(3):371–402.

Rodrigues, D. S., Faroni, W., Santos, N. A., Ferreira, M. A. M., and Diniz, J. A. (2020). Corrupção e má gestão nos gastos com educação: fatores socioeconômicos e políticos. Revista de Administração Pública [online], 54(2):301–320.

Silva, A. L., Sampaio, V. G. R. C. A., Lima, A. M. A., Cabral, G. G., and Valença, G. (2024a). Ferramenta para auxílio à auditoria de editais municipais para compra de medicamentos. In Anais do XX Simpósio Brasileiro de Sistemas de Informação (SBSI).

Silva, E. C., Medeiros, I. P., Menezes, M. V., and Kamikawachi, D. S. L. (2024b). Segmentation and summarization for extracting information about information technology equipment from government procurement notice. In Symposium on Knowledge Discovery, Mining and Learning (KDMILE). Sociedade Brasileira de Computação.

Silva, M., Santos, E., Alves, K., Silva, H., Pedrosa, F., Valença, G., and Brito, K. (2024c). Using generative ai for simplifying official documents in the public accounts domain. In Anais do Workshop de Computação Aplicada em Governo Eletrônico (WCGE).

Topchii, V., Zadereiko, S., Didkivska, G., Bodunova, O., and Shevchenko, D. (2021). International anti-corruption standards. Baltic J. of Economic Studies, 7(5):277–286.

United Nations (2015). Transforming our world: The 2030 agenda for sustainable development. Accessed: 2025-02-07.