Supporting scientific knowledge discovery with extended, generalized Formal Concept Analysis

• We present a methodology for scientific enquiry based in Formal Concept Analysis.
• We adopt the “Landscapes of Knowledge” metaphor for Exploratory Data Analysis.
• We provide use cases to demonstrate the affordances of the methodology.
• The use cases encompass gene expression data and classifier assessment.
• The use cases also include abstract algebra and information extraction and indexing.

In this paper we fuse together the Landscapes of Knowledge of Wille’s and Exploratory Data Analysis by leveraging Formal Concept Analysis (FCA) to support data-induced scientific enquiry and discovery.We use extended FCA first by allowing KK-valued entries in the incidence to accommodate other, non-binary types of data, and second with different modes of creating formal concepts to accommodate diverse conceptualizing phenomena.With these extensions we demonstrate the versatility of the Landscapes of Knowledge metaphor to help in creating new scientific and engineering knowledge by providing several successful use cases of our techniques that support scientific hypothesis-making and discovery in a range of domains: semiring theory, perceptual studies, natural language semantics, and gene expression data analysis.While doing so, we also capture the affordances that justify the use of FCA and its extensions in scientific discovery.