Data Science Track

Gaining insight from data is the overarching goal of many Data Science related activities. However, without understanding the semantics of data and without having the means and techniques to represent semantics in a machine-processable form, insights could turn into wrong or misleading perceptions.

Since we strongly believe that people and scientific communities can learn from each other, this year, SEMANTiCS will feature a special Data Science track, which should close the gap between data science and semantics research. SEMANTiCS has a long-standing tradition in providing methods and techniques for representing data in an interoperable, standardized, and machine-processable fashion. By including researchers and practitioners interested in Data Science, we hope that we can bring together people with various backgrounds and goals to learn from each other and to stimulate a joint future research agenda at the intersection of semantics and data science research and practice.


What can you expect?

This year’s Data Science track will cover research and innovation papers as well as industry and use case presentations and stretch over both conference days. It includes  sessions about typical steps in a data science workflow, ranging from “Data Normalization and Aggregation” to “Mining and Linking” and “Anomaly Detection”.

Special presentation format

Furthermore, we have decided to give it a try and allow a special presentation format, which should encourage the audience to actively participate in discussions around synergies, key problems and solutions, common questions, etc. This will be the first session, called “Data Normalization and Aggregation”, which will moderated by team members from the “Association for Knowledge Management”. 


We, the chairs of the overall data science tracks are happy that the Data Science track attracted more than enough interest to be included in this year’s program of SEMANTiCS. We are looking forward to meet and exchange ideas with people who share similar interests and are convinced that this year’s SEMANTiCS will be a good place to start these discussions.

Bernhard Haslhofer and Laura Hollnik
Data Science Track Chairs


The Track

Tuesday, 12.09.2017
10:30- 12:00 Room 6+7
  Session 1.6: Data Science
  Data Normalization & Aggregation
  Slovak Public Metadata Governance and Management based on Linked Data (Datalan, Miroslav Líška)
  NERDing out: Job Title Normalisation in an Online Employment Marketplace (SEEK Limited, Jane Frazier)
  Fostering Interoperability of European Qualifications: The Qualification Data Repository (QDR) (Cognizone BVBA, Agis Papantoniou)
16:05 - 17:35 Room 6+7
  Session 2.6 Data Science
  Querying and Visualization
  Cognitive Probability Graphs for Knowledge Management (Franz Inc., Jans Aasman)
  Semantic Data Governance for Regulatory Compliance (TopQuadrant,Inc., Hodgson Ralph)
  LOD-a-lot: A Single-File Enabler for Data Science (Wouter Beek, Javier D. Fernández and Ruben Verborgh) *
Wednesday, 13.09.2017
10:15 - 11:15 Room 6+7
  Session 3.6 Data Science
  The Data Platform of the Future - Large Base Registries of the Netherlands (Kadaster, Erwin Folmer)
  Good Applications for Crummy Entity Linkers? The Case of Corpus Selection inDigital Humanities (Alex Olieman, Kaspar Beelen, Jaap Kamps and Milan van Lange)
11:45 - 12:45 Room 6+7
  Session 4.5 Data Science
  Text Mining and Linking
  euBusinessGraph Company and Economic Data for Innovative Products and Services (Ontotext AD, Atanas Kiryakov, Plamen Tarkalanov, Vladimir Alexiev)
  Investigating the interpretability of hidden layers in deep text mining (Stephan Raaijmakers, Maya Sappelli and Wessel Kraaij)
15:05 - 16:05 Room 6+7
  Session 5.6 Data Science
  Anomaly Detection
  Towards a Semantic Outlier Detection Framework in WirelessSensor Networks (Iker Esnaola-Gonzalez, Jesús Bermúdez, Izaskun Fernandez, Santiago Fernandez and Aitor Arnaiz)
  VAT Fraud detection with streaming reasoning (Cognitum, Alessandro Seganti)