Interactive Collaborative Exploration using Incomplete Contexts
This work addresses a gap in knowledge acquisition for domain experts in Formal Concept Analysis, but it is incremental as it extends existing methods to a multi-expert setting.
The paper tackles the problem of attribute exploration in Formal Concept Analysis by developing a theoretical framework for multiple experts to collaborate using incomplete knowledge represented as three-valued contexts, without presenting concrete numerical results.
A well-known knowledge acquisition method in the field of Formal Concept Analysis (FCA) is attribute exploration. It is used to reveal dependencies in a set of attributes with help of a domain expert. In most applications no single expert is capable (time- and knowledge-wise) of exploring the knowledge domain alone. However, there is up to now no theory that models the interaction of multiple experts for the task of attribute exploration with incomplete knowledge. To this end, we to develop a theoretical framework that allows multiple experts to explore domains together. We use a representation of incomplete knowledge as three-valued contexts. We then adapt the corresponding version of attribute exploration to fit the setting of multiple experts. We suggest formalizations for key components like expert knowledge, interaction and collaboration strategy. In particular, we define an order that allows to compare the results of different exploration strategies on the same task with respect to their information completeness. Furthermore we discuss other ways of comparing collaboration strategies and suggest avenues for future research.