A new model of evaluating concept similarity

In this paper, a new similarity model is proposed, which based on rough set to evaluate the similarity degree of the two concepts of concept lattice. The proposed method combines featural and structural information into decision and has a higher correlation with human judgement, which can be viewed as the development of Tversky’s similarity model. Compared with other similarity models this approach is convenient to measure the similarity of the concepts of the large contexts, by which we can avoid constructing Hasse diagram and looking through all concepts of the context.