BioNav: Effective Navigation on Query Results of Biomedical Databases

Abstract

Abstract-Search queries on biomedical databases like PubMed often return a large number of results, only a small subset of which is relevant to the user. Ranking and categorization, which can also be combined, have been proposed to alleviate this information overload problem. Results categorization for biomedical databases is the focus of this work. A natural way to organize biomedical citations is according to their MeSH annotations. MeSH is a comprehensive concept hierarchy used by PubMed. In this paper, we present the BioNav system, a novel search interface that enables the user to navigate large number of query results by organizing them using the MeSH concept hierarchy. First, the query results are organized into a navigation tree. At each node expansion step, BioNav reveals only a small subset of the concept nodes, selected such that the expected user navigation cost is minimized. In contrast, previous works expand the hierarchy in a predefined static manner, without navigation cost modelling. We show that the problem of selecting the best concepts to reveal at each node expansion is NP-complete and propose an efficient heuristic as well as a feasible optimal algorithm for relatively small trees. We show experimentally that BioNav outperforms state-of-the-art categorization systems with respect to the user navigation cost. We have implemented BioNav for the MEDLINE database at http://db.cse.buffalo.edu/bionav.

Comprehension-based result snippets

“…Recent works [6,15] have studied the problem of what attributes to display to minimize the user effort, but operate on flat relations of products without any classification. BioNav [5] presents the bibliographic results of queries on PubMed on an ontological hierarchy and allows users to effectively navigate on that hierarchy.…”

“…Hence, naturally the query answer typically consists of a list of heterogeneous objects, due to the ambiguous nature of keyword queries. Query interfaces use a variety of methods to help users find the results that they are most interested in, like ranking [1][2][3], categorization (facets) [4][5][6], and result snippets.…”

Exploring biomedical databases with BioNav

“…BioNav, first proposed in [1], introduces a dynamic navigation method that depends on the particular query result at hand. The query results are attached to the corresponding MeSH concept nodes as in Figure 1, but then the navigation proceeds differently.…”

Navigation Cost Modeling Based On Ontology

“…The cost of navigation is directly proportionate to the navigation subtree instead of the whole results in the tree. Earlier work on dynamic categorization of query results are in [3], [4], [10] and [6]. They made use of query dependent clusters based on the unsupervised technique.…”