ABSTRACT:

Search queries on biomedical databases, like PubMed, usually come back a giant number of results, solely a small subset of that is relevant to the user. Ranking and categorization, which will also be combined, have been proposed to alleviate this info overload problem. Results categorization for biomedical databases is the main focus of this work. A natural approach to prepare biomedical citations is in keeping with their MeSH annotations. MeSH may be a comprehensive concept hierarchy used by PubMed. In this paper, we gift the BioNav system, a completely unique search interface that enables the user to navigate large range of question results by organizing them using the MeSH concept hierarchy. First, the query results are organized into a navigation tree. At each node growth step, BioNav reveals solely a small subset of the concept nodes, selected such that the expected user navigation price is minimized. In distinction, previous works expand the hierarchy during a predefined static manner, without navigation cost modeling. We show that the matter of choosing the simplest ideas to reveal at each node expansion is NP-complete and propose an economical heuristic plus a feasible optimal algorithm for comparatively little trees. We have a tendency to show experimentally that BioNav outperforms state-of-the-art categorization systems by up to an order of magnitude, with respect to the user navigation value.