Using Concept Lattices for Text Retrieval and Mining

The potentials of formal concept analysis (FCA) for information retrieval (IR) have been highlighted by a number of research studies since its inception. With the proliferation of small-size specialised text databases available in electronic format and the advent of Web-based graphical interfaces, FCA has then become even more appealing and practical for searching text collections. The main advantage of FCA for IR is the possibility of eliciting context, which may be used both to improve the retrieval of specific items from a text collection and to drive the mining of its contents. In this paper, we will focus on the unique features of FCA for building contextual IR applications as well as on its most critical aspects. The development of a FCA-based application for mining the web results returned by a major search engine is envisaged as the next big challenge for the field.