Fuzzy Similarity Measure Model for Trees with Duplicated Attributes

Abstract

In many business situations, complex user profiles are described by tree structures, and evaluating the similarity between these trees is essential in many applications, such as recommender systems. This paper proposes a fuzzy similarity measure model for trees with duplicated attributes. In this model, the conceptual similarity between attributes and the weights of nodes are expressed by linguistic terms. To deal with duplicated attributes in the trees, nodes with the same concept are clustered. The most conceptual corresponding cluster pairs among two trees are identified. Based on the corresponding cluster pairs, the conceptual similarity and the value similarity between two trees are evaluated, and the final similarity measure is assessed as a weighted sum of their conceptual and value similarities.