Knowledge Discovery Model Based on Semantic and Temporal Associations between Textual Elements

The vast amount of digital data currently available has great potential for pattern analysis and knowledge discovery. Especially, relationship analysis can provide new and possibly unexpected insights. Thus, this work proposes a model for knowledge discovery based on semantic and temporal associations between textual elements, which has a high-level ontology for the representation of relationships and the Singular Value Decomposition (SVD) technique to determine the strength of association between terms that are not directly related. The evaluation of the model was performed from experiments that reproduce seminal findings in the area. The results demonstrate that the model is able to present the evolution of associative force between two terms over time, contributing to the discovery of knowledge.