Análise comparativa de algoritmos de mineração de texto aplicados a históricos de contas públicas

• Autor(a) principal: Santos, Breno Santana
• Data de Publicação: 2015
• Tipo de documento: Trabalho de conclusão de curso
• Idioma: por
• Título da fonte: Repositório Institucional da UFS
• Texto Completo: http://ri.ufs.br/jspui/handle/riufs/7120
• topic: Algoritmos; Mineração de Texto; Histórico de Contas Públicas; Avaliação de Desempenho e Qualidade; Algoritmos de computador; Inteligência artificial; Text Mining Algorithms; Public Accounts History; Performance and Quality Assessment; CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO

Using Text Mining (TM) is important in the process of knowledge extraction from text bases. However, it is important to assess if the knowledge extracted or produced is relevant or not to the user. Ahead of these verifications, it objectified, with this work, in the ambit of the audit activities performed in the Audit Office of the Country of Sergipe (AOC-SE), the development of a text mining algorithm for TextMining tool (MT solution of the AOC-SE), as well as performance evaluating of the tool text mining algorithms. This evaluation was performed by a case study in the public accounts of historical to detect irregularities in the payment of daily.