Computing Entity Semantic Similarity by Features Ranking

TL;DR

This paper introduces a new method for estimating semantic similarity between entities by comparing ranked feature lists derived from Linked Data, demonstrating improved accuracy over existing measures.

Contribution

It proposes a novel feature ranking approach for entity similarity estimation using Linked Data, validated with experiments on museum, catalog, and conference datasets.

Findings

Enhanced accuracy over state-of-the-art similarity measures

Effective use of ranked feature lists from Linked Data

Validated across diverse datasets

Abstract

This article presents a novel approach to estimate semantic entity similarity using entity features available as Linked Data. The key idea is to exploit ranked lists of features, extracted from Linked Data sources, as a representation of the entities to be compared. The similarity between two entities is then estimated by comparing their ranked lists of features. The article describes experiments with museum data from DBpedia, with datasets from a LOD catalog, and with computer science conferences from the DBLP repository. The experiments demonstrate that entity similarity, computed using ranked lists of features, achieves better accuracy than state-of-the-art measures.