A New Statistical and Verbal-Semantic Approach to Pattern Extraction in Text Mining Applications

Abstract

The discovery of knowledge in textual databases is an approach that basically seeks for implicitrelationships between different concepts in different documents written in natural language, inorder to identify new useful knowledge. To assist in this process, this approach can count on thehelp of Text Mining techniques. Despite all the progress made, researchers in this area must stilldeal with the large number of false relationships generated by most of the available processes.A statistical and verbal semantic approach that supports the understanding of the logic betweenrelationships may bridge this gap. Thus, the objective of this work is to support the user with theidentification of implicit relationships between concepts present in different texts, consideringthe causal relationships between concepts in the texts. To this end, this work proposes a hybridapproach for the discovery of implicit knowledge present in a text corpus, using analysis based onassociation rules together with metrics from complex networks and verbal semantics. Througha case study, a set of texts from alternative medicine was selected and the different extractionsshowed that the proposed approach facilitates the identification of implicit knowledge by theuser