On-Demand Generation of AOC-Posets: Reducing the Complexity of Conceptual Navigation

Exploratory search allows to progressively discover a dataspace by browsing through a structured collection of documents. Concept lattices are graph structures which support exploratory search by conceptual navigation, i.e., navigating from concept to concept by selecting and deselecting descriptors. These methods are known to be limited by the size of concept lattices which can be too large to be efficiently computed or too complex to be browsed intelligibly. In this paper, we address the problem of providing techniques that reduce the complexity of FCA-based exploratory search. We show the suitability of AOC-posets, a condensed alternative structure to achieve conceptual navigation. Also, we outline algorithms to enable an on-demand generation of AOC-posets. The necessity to devise more flexible methods to perform product selection in software product line engineering is what motivates our work.