=Paper=
{{Paper
|id=Vol-1594/paper1
|storemode=property
|title=None
|pdfUrl=https://ceur-ws.org/Vol-1594/paper1.pdf
|volume=Vol-1594
}}
==None==
<pdf width="1500px">https://ceur-ws.org/Vol-1594/paper1.pdf</pdf>
<pre>
       Mining and Managing Large-Scale Linked Open Data
                                                              [Abstract]
                                                           Ansgar Scherp
                                                          University of Kiel
                                                     Christian-Albrechts-Platz 4
                                                             24118 Kiel
                                                  asc@informatik.uni-kiel.de

ABSTRACT                                                                  About the Author
Linked Open Data (LOD) is about publishing and interlin-                  Ansgar Scherp is Professor for Knowledge Discovery with
king data of different origin and purpose on the web. The                 ZBW - Leibniz Information Centre for Economics and Kiel
Resource Description Framework (RDF) is used to descri-                   University since January 2014. He is expert on analyzing
be data on the LOD cloud. In contrast to relational data-                 Linked Open Data, the approach to publish and interlink
bases, RDF does not provide a fixed, pre-defined schema.                  data on the web. Ansgar has been EU Marie Curie Fellow
Rather, RDF allows for flexibly modeling the data schema                  at UC Irvine, CA, USA from 2006 to 2007. Subsequently,
by attaching RDF types and properties to the entities. Our                he has led work packages in EU projects such as WeKno-
schema-level index called SchemEX allows for searching in                 wIt and Social Sensor at the University of Koblenz-Landau.
large-scale RDF graph data. The index can be efficiently                  Currently, Ansgar is scientific coordinator of the EU H2020
computed with reasonable accuracy over large-scale data                   project MOVING (http://moving-project.eu/) on training
sets with billions of RDF triples, the smallest information               users from all societal sectors to improve their information
unit on the LOD cloud. SchemEX is highly needed as the si-                literacy by training how to choose, use, and evaluate data
ze of the LOD cloud quickly increases. Due to the evolution               mining methods in connection with their daily research tasks
of the LOD cloud, one observes frequent changes of the data.              and to become data-savvy information professionals.
We show that also the data schema changes in terms of com-
binations of RDF types and properties. As changes cannot
capture the dynamics of the LOD cloud, current work inclu-
des temporal clustering and finding periodicities in entity
dynamics over large-scale snapshots of the LOD cloud with
about 100 million triples per week for more than three years.




28th GI-Workshop on Foundations of Databases (Grundlagen von Daten-
banken), 24.05.2016 - 27.05.2016, Nörten-Hardenberg, Germany.
Copyright is held by the author/owner(s).




                                                                      8

</pre>