Instance-based ontology mapping comprises a collection of theoretical approaches and applications for identifying the implicit semantic similarities between two ontologies on the basis of the instances that populate their concepts. The current paper situates this general problem in the realm of finding mappings between the nodes of two different web directories populated with text documents (the web pages that they intend to organize). We propose a novel approach to detect potential concept mappings based on Principle Component Analysis and Discriminant Analysis and introduce a resulting concept similarity measure. The procedure can be used as an independent concept mapping technique, or as a support to a concept similarity measure of other nature.