A Formal Description-Based Approach to Extended Many-Valued Context Analysis

Abstract

Formal Concept Analysis (FCA) is an effective formal tool for data analysis and knowledge mining. The paper firstly proposed a semi-automatic method, which is based on extended description, is used to translate the original documents into extended many-valued context. Then based on extended many-valued contexts and extended description, the paper presented an approach to concept lattice analysis in order to improve the utility and pertinence to the concept lattice. The method allows to avoid the generation of a large one-valued context and to do document knowledge discovery.