Advanced search
Start date
Betweenand

KGevol: dynamic knowledge graphs extracted from unstructured textual information

Abstract

Knowledge is often conveyed in texts from various nature. Given the massive amountof texts structured in different formats available on the Web, extracting knowledge with computational tools and building knowledge representations can lead great benefits to stakeholders. As knowledge evolves, new texts are produced, documenting new facts that denote newer aspects brought by the evolution. Characterizing such evolution via knowledge representations suited to evolve over time can entail several benefits for domain analysis. If we consider temporal sets of texts, for instance, articles documenting knowledge produced in scientific investigations, a proper representation of such knowledge and its evolution might benefit researchers, the scientific community, and consequently, the overall society. This project aims to study novel methods to represent knowledge conveyed in textual documents. Our investigation aims to characterize the evolution of facts extracted from texts and represent them in knowledge graphs. We introduce novel methods that exploit the concept of Temporal Knowledge Graphs to model the temporal evolution of knowledge in corpora of unstructured texts. In our approach, complex network measurements are applied over temporal knowledge graphs to determine the relevance of concepts dealt within the textual corpora under analysis. We investigate novel visual representations of such evolution to help in knowledge analysis over time. (AU)

Articles published in Agência FAPESP Newsletter about the research grant:
More itemsLess items
Articles published in other media outlets ( ):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)

Scientific publications
(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)
VICTORELLI, ELIANE ZAMBON; DOS REIS, JULIO CESAR. Evaluating User Experience in Information Visualization Systems: UXIV an Evaluation Questionnaire. HUMAN INTERFACE AND THE MANAGEMENT OF INFORMATION, HIMI 2023, PT I, v. 14015, p. 19-pg., . (13/08293-7, 15/16528-0, 22/15816-5)