COVID-19 Deep Clustering: An Ontology construction clustering method with dynamic medical labeling

This paper introduces a novel clustering-based framework for COVID-19 ontology construction using Pubmed LitCovid scientific research articles data. Our study uses a semantic approach with hierarchical clustering to construct a more effective COVID-19 documents ontology with medical labeling and search. We believe this study may initiate a future development for an advanced COVID-19 domain-specific ontology. The significant contribution from this research addresses solving the limitations in manual classification tasks of the everyday fast-increasing number of scientific papers and the overloading of their unclassified knowledge. With this research, our provision will help scholars with a better search mechanism to retrieve highly relevant expert information about their favorite topics in the COVID-19-related literature. To our best knowledge, this approach is the first successful attempt to apply auto clustering with labeling and search on the COVID-19 research papers. Moreover, in text processing, we propose a systematical evaluation without dependence on standard data collection to evaluate our methodology.