10.6084/m9.figshare.7509314.v1 Bruno Missi Xavier Bruno Missi Xavier Alcione Dias da Silva Alcione Dias da Silva Geórgia Regina Rodrigues Gomes Geórgia Regina Rodrigues Gomes A hybrid architecture for document indexing of the Municipal Official Gazette in Cachoeiro de Itapemirim SciELO journals 2018 Official Gazette Cachoeiro de Itapemirim Indexing documents Text mining Information retrieval 2018-12-26 03:32:54 Dataset https://scielo.figshare.com/articles/dataset/A_hybrid_architecture_for_document_indexing_of_the_Municipal_Official_Gazette_in_Cachoeiro_de_Itapemirim/7509314 <p></p><p>Text mining techniques have been widely used to process large volumes of documents. However, there is still a large gap when defining the architecture for systems with transactional elements of computational intelligence. The aim of the paper is to outline a proposed architecture to build a computational system that uses text mining techniques to index content from the database of the Official Gazette in the city of Cachoeiro de Itapemirim in the state of Espírito Santo, transforming the information previously available in natural language into a structured format that can be persisted. To validate the architecture we developed a prototype in Java accessible in the Web environment to evaluate the tool. To evaluate the tool, a case study featured a database composed of 22 documents, containing 198 normative acts from the database of the Official Gazette, in which good levels of accuracy and coverage of information retrieval were identified. This study contributes to the presentation of a hybrid architecture consisting of components of the model of transactional systems and elements of text mining, in addition to the use of software design patterns.</p><p></p>