Data Linking

Benjamin Zapilko

Wissenstechnologien für Sozialwissenschaften

Data Linking
Teamleiter(in)

+49 (221) 47694-515
E-Mail
vCard

Benjamin Zapilko

In the field Data Linking, models and approaches are investigated that enable the detection and linking of entities as well the integration of heterogeneous data sources. Technologies like Text Mining and Semantic Web (e.g. Linked Open Data) play a significant role. They allow a technical interpretation and connection of information and data as well as for facilitating collaboration in the web. Thus, a quality increase of the web from user perspective can be achieved.

At GESIS, the research activities in the field of Data Linking are focused on the detection, disambiguation und linking of social science relevant entities in scientific publications (like persons, institutions, locations, citations, research data) and other heterogeneous information types by applying Text Mining and Machine Learning technologies. Another focus is the development of methods for linking heterogeneous research data (e.g. geographical data) to data sources from the web in order to enable a combined analysis of these connected data sources.

Publications

  • Schaible, Johann, Pedro Szekely, and Ansgar Scherp. 2016 (Forthcoming). "Comparing Vocabulary Term Recommendations using Association Rules and Learning To Rank: A User Study." In THE SEMANTIC WEB. LATEST ADVANCES AND NEW DOMAINS
  • Schaible, Johann, Thomas Gottron, and Ansgar Scherp. 2016 (Forthcoming). "TermPicker: Enabling the Reuse of Vocabulary Terms by Exploiting Data from the Linked Open Data Cloud." In THE SEMANTIC WEB. LATEST ADVANCES AND NEW DOMAINS
  • Zapilko, Benjamin, Johann Schaible, Timo Wandhöfer, and Peter Mutschke. 2015. "Applying linked data technologies in the social sciences." Künstliche Intelligenz : KI online first 1-4. doi: http://dx.doi.org/10.1007/s13218-015-0416-6. http://link.springer.com/article/10.1007/s13218-015-0416-6?wt_mc=internal.event.1.SEM.ArticleAuthorOnlineFirst.
  • Zapilko, Benjamin, and Brigitte Mathiak. 2014. "Object property matching utilizing the overlap between imported ontologies." In The Semantic Web: Trends and Challenges ; 11th International Conference, ESWC 2014, Anissaras, Crete, Greece, May 25-29, 2014 ; Proceedings, edited by Valentina Presutti, Claudia d'Amato, and Fabien Gandon, Lecture Notes in Computer Science ; vol. 8465, 737-751. Cham: Springer. http://2014.eswc-conferences.org/sites/default/files/papers/paper_65.pdf.
  • Boland, Katarina, Dominique Ritze, Kai Eckert, and Brigitte Mathiak. 2012. "Identifying References to Datasets in Publications." TPDL 2012 : Theory and Practice of Digital Libraries, Paphos.