# Observing LOD using Equivalent Set Graphs: it is mostly flat and sparsely linked

## TL;DR

This paper empirically analyzes the structure of Linked Open Data, revealing its flat and sparsely linked nature, and introduces a framework and tools for further analysis of such data.

## Contribution

It provides a novel conceptual framework with metrics and an open source tool for analyzing the semantic structure of Linked Open Data.

## Key findings

- LOD is mostly flat and sparsely linked
- Hierarchies of concepts are loosely structured
- The framework and tools facilitate LOD analysis

## Abstract

This paper presents an empirical study aiming at understanding the modeling style and the overall semantic structure of Linked Open Data. We observe how classes, properties and individuals are used in practice. We also investigate how hierarchies of concepts are structured, and how much they are linked. In addition to discussing the results, this paper contributes (i) a conceptual framework, including a set of metrics, which generalises over the observable constructs; (ii) an open source implementation that facilitates its application to other Linked Data knowledge graphs.