Recuperação da Informação em Ambientes Semânticos: uma ferramenta aplicada à publicações científicas

Abstract

The data available on the Web is growing exponentially, providing information of high added value to organizations. Such information can be arranged in diverse bases and in varied formats, like videos and photos in social media. However, unstructured data present great difficulty for the information retrieval, not efficiently meeting the informational needs of the users, because there are problems in understanding the meaning of documents stored on the Web. In the context of an Information Retrieval architecture, this research aims to The implementation of a semantic extraction agent in the context of the Web that allows the location, treatment and retrieval of information in the context of Big Data in the most varied informational sources that serves as the basis for the implementation of informational environments that aid the Information Retrieval process , Using ontology to add semantics to the process of retrieval and presentation of results obtained to users, thus being able to meet their needs.