Data Extraction Optimization Tool from Police Reports
a Case Study in the Diretoria Estadual de Combate a Crimes Cibernéticos of Polícia Civil do Estado do Pará
DOI:
https://doi.org/10.5752/P.2316-9451.e2025130101Keywords:
Cybercrimes, Data leak, Data extraction tool, Theory of regular languages, Police reportsAbstract
Driven by the incentive to develop innovative solutions in the fight against cybercrime, this article proposes a tool to automatically extract data from police reports. The tool was based on the foundations of formal language theory and implemented using regular expressions. The tool’s performance was assessed using a labeled dataset by computing the precision and recall metrics. The pilot study demonstrated the tool’s efficiency, with precision and recall rates exceeding 0.9, showcasing its potential to uncover valuable information and patterns for police investigations.
Downloads
Downloads
Published
How to Cite
Issue
Section
License
I (we) submit the present work, an original and unpublished manuscript, from my (our) authorship, to Abakós - Magazine of Interdisciplinary Studies on Science and Informatics, and I (we) agree that the copyright related to this work will become property of PUC Minas Publisher. No partial or full reproduction is allowed, by any means (printed or electronic), dissociated from Abakós. Any reproduction requires prior written authorization granted by the Editor.
I (we) declare there is no type of interest conflict among the subject theme, author(s), organization(s), institution(s) and person(s).
I (we) recognize that Abakós is licensed under CREATIVE COMMONS:
Licença Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported (CC BY-NC-ND 3.0).