Text Mining Methods for Unifying Strategic Planning Indicators in the Municipalities of Mato Grosso

Authors

  • Lia Hanna Martins Morita UFMT
  • Rita de Cássia Cruz Universidade Federal do Mato Grosso https://orcid.org/0009-0009-2867-0501
  • Anderson Castro Soares de Oliveira

Keywords:

Text Mining, Regular Expressions, Strategic Planning, Monitoring indicators, Municipalities of Mato Grosso State

Abstract

Indicators are essential tools for resource management and monitoring public policies in municipalities. In the state of Mato Grosso, the Strategic Planning Management Program (GPE), developed in collaboration with the Tribunal de Contas, is an initiative that seeks to enhance public policies by adopting standardized indicators. Within this framework, text mining emerges as a valuable technique for analyzing and processing vast amounts of data in documents and reports. Regular expressions are sequences of characters in a text that follow a specific pattern, such as words accented with acute, circumflex, tilde, or grave accents. These patterns can be detected through algorithms, then replaced or removed. For example, if the objective is to remove the accent from all words in a sentence, algorithms can be employed likewise. Another assignment of interest is standardizing text to lowercase or title case using regular expressions. Such modifications streamline daily tasks and aid in the framing of managing reports, as standardized texts are more straightforward to analyze, derive insights from, and base business decisions on. In this study, text mining techniques and regular expressions were employed to standardize the nomenclature of indicators from municipalities participating in the GPE, thereby enhancing their management and oversight. Text mining allowed for a systematic analysis of the data, pinpointing improvement, correcting inconsistencies, and thereby bolstering the efficacy of public policies.

References

DE OLIVEIRA, M.W.P.; NEDER, R.; RAMALHO, P.; MACIEL, C.; FREIRE, N.; PERES, J.; VUOLO, C.; ANJOS, A. MANSILLA, D. Indicators of Municipal Public Management: Study of Multiple Performance Measurement Systems. In: KŐ, A. et al. Electronic Government and the Information Systems Perspective. EGOVIS 2019. Lecture Notes in Computer Science, v. 11709. Cham: Springer, 2019. Disponível em: https://link.springer.com/chapter/10.1007/978-3-030-27523-5_9

FEINERER, I.; HORNIK, K. tm: Text Mining Package. R package v. 0.7-11, 2023. Disponível em: https://cran.r-project.org/package=tm

FELDMAN, R.; SANGER, J. The Text Mining Handbook: Advanced Approaches in Analyzing Unstructured Data. Cambridge: Cambridge University Press, 2007.

FITZPATRICK, J. L.; SANDERS, J. R.; WORTHEN, B. R. Program Evaluation: alternative approaches and practical guidelines. 4. ed. New Jersey: Pearson, 2011.

FRIEDL, J. E. F. Mastering Regular Expressions. Sebastopol: O'Reilly Media, 2006.

GRUBER, J. LexisNexisTools. An R package for working with newspaper data from 'LexisNexis'. R package v. 0.3.5, 2023. Disponível em: https://github.com/JBGruber/LexisNexisTools.

JANNUZZI, P. M. Monitoramento e avaliação de programas sociais: uma introdução aos conceitos e técnicas. Campinas, SP: Editora Alínea, 2016.

JANNUZZI, P. M. A importância da informação estatística para as políticas sociais no Brasil: breve reflexão sobre a experiência do passado para considerar no presente. Revista Brasileira de Estudos de População, São Paulo, v. 35, n. 1, e0055, 2018.

JURAFSKY, D.; MARTIN, J. H. Speech, and Language Processing: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition. 3. ed. New Jersey: Pearson Education, 2020.

KAPLAN, R.; NORTON, D. The Balanced Scorecard - Measures That Drive Performance. Harvard Business Review, n. 01, pp.71-79, jan-fev, 1992.

KAPLAN, R.; NORTON, D. Using the balanced scorecard as a strategic management system. Harvard Business Review, n. 01, pp.75-85, jan-fev, 1996.

KIRCH, J. L.; SCHOENHERR, R. P.; VELOSO, T. C. M. A.; HONGYU, K. Aplicação da Análise de Componentes Principais e de Agrupamento para os Indicadores de Desempenho das Universidades Federais do Brasil. Sigmae, 8(2), 55-66, 2019. Disponível em: https://publicacoes.unifal-mg.edu.br/revistas/index.php/sigmae/article/view/920

LEE, J.; YOON, Y. Indicators development to support intelligent road infrastructure in urban cities. Transport Policy, v. 114, p.252-265, 2021.

MATO GROSSO. PDI – Programa de Desenvolvimento Institucional Integrado: TCE-MT, promovendo soluções inovadoras na linha de sua missão orientadora compartilha com os fiscalizados a experiência adquirida a partir da adoção do planejamento estratégico e de novas tecnologias, para a eficiência da administração pública. Cuiabá: TCE, 2013.

MATO GROSSO. Tribunal de Contas do Estado. Resolução Normativa nº 14/2022 de 28 de junho de 2022. Dispõe sobre a instituição do Programa de Apoio à Gestão do Planejamento Estratégico dos Municípios, denominado GPE, no âmbito do Tribunal de Contas do Estado de Mato Grosso. Cuiabá: TCE, 2022.

MODRUŠAN, N.; MRŠIĆ, L.; RABUZIN, K. Intelligent Public Procurement Monitoring System Powered by Text Mining and Balanced Indicators. In: Hammoudi, S. et al. Data Management Technologies and Applications. DATA 2020. Communications in Computer and Information Science, v. 1446. Cham: Springer, 2021.

MOREIRA, D.; SANTINI, J. F. Conectando Pesquisa a Gestão Municipal: Avaliações de Impacto Influenciam a Formação de Política Pública? In: KOGA, Natália Massaco et al. Políticas Públicas e Usos de Evidências no Brasil: Conceitos, Métodos, Contextos e Práticas. 1. ed. Brasília: Ipea, 2022.

R CORE TEAM. R: A language and environment for statistical computing. Vienna: R Foundation for Statistical Computing, 2022. Disponível em: https://www.R-project.org/.

RINKER, T. W. textclean: Text Cleaning Tools, v. 0.9.3. Buffalo, New York, 2018. Disponível em: https://github.com/trinker/textclean.

SHIBUI, S. Visualization of indicators to enhance the internal quality assurance system in Japanese universities. International Conference on Research in Education, Teaching and Learning, Paris, p. 16, 2018.

SILVA, I. P. Indicadores Sociais e Sua Importância para a Gestão Pública Municipal. 2022. 52 f. Trabalho de Conclusão de Curso (Especialização) - Universidade Federal Rural de Pernambuco, Especialização em Gestão Pública Municipal, Recife, 2022.

ZIZKA, J.; DARENA, F.; SVOBODA, A. Text Mining with Machine Learning: Principles and Techniques. 1. ed. Boca Raton: CRC Press, 2019.

Published

31-12-2023

How to Cite

Hanna Martins Morita, L., Cruz, R. de C., & de Oliveira, A. C. S. (2023). Text Mining Methods for Unifying Strategic Planning Indicators in the Municipalities of Mato Grosso. Sigmae, 12(3), 39–50. Retrieved from https://publicacoes.unifal-mg.edu.br/revistas/index.php/sigmae/article/view/2219

Issue

Section

Data Science & Machine Learning