Dynamic Integration and Visualization of Information from Multiple Evidence Sources

  • Hornik, Kurt (PI - Project head)
  • Panny, Wolfgang (PI - Project head)
  • Wohlgenannt, Gerhard (PI - Project head)
  • Belk, Stefan (Researcher)
  • Föls, Michael (Researcher)
  • Rafelsberger, Walter (Researcher)
  • Syed, Kamran Ali Ahmad (Researcher)

Project Details

Description

Content providers and analysts alike increasingly rely on combining multiple data sources to build comprehensive, up-to-date and properly interlinked information spaces. These organizations criticallydepend on technologies for integrating these sources and tracking their evolution. DIVINE aims to provide such technologies, with a lightweight seed ontology acting as the focal point for integrating new evidence derived from multiple, evolving data sources. As such, the project advances ontology evolution research characterized by single-source solutions, which exploit mostly textual and rather static data. DIVINE integrates structured, unstructured and social sources. A modu-
lar and scalable portfolio of evidence acquisition services crawls public Web documents, queries Linked Open Data repositories, aggregates resource annotations from Web 2.0 applications, and triggers validation processes for missing or conflicting evidence. Since evidence from third-party sources is inherently uncertain, source-specific transformation rules and impact factors assign a confidence value to each new fact. A spreading activation network utilizes the collected evidence in conjunction with the confidence values for extending the seed ontology.

DIVINE will monitor domain changes over time to derive knowledge evolution patterns. This domain-centric view makes DIVINE novel among existing change detection approaches, which tend to be domain-agnostic. Each ontology element is assigned a confidence matrix, which records the changes in confidence values over time. Data services and dynamic visualizations reveal rising, declining or cyclic patterns in the confidence matrices. Such patterns are important indicators - the rate of change or the date of a concept's first appearance, for example, shed light on the evolution of knowledge and on the underlying processes that drive this evolution.

Financing body

Austrian Research Promotion Agency
StatusFinished
Effective start/end date1/07/1123/06/13

Collaborative partners

Austrian Classification of Fields of Science and Technology (OEFOS)

  • 102 not use (legacy)
  • A Prototype for Automating Ontology Learning and Ontology Evolution

    Wohlgenannt, G., Belk, S. & Schett, M., 1 Oct 2013, 5th International Conference on Knowledge Engineering and Ontology Development (KEOD-2013). Joaquim Filipe and Jan Dietz (ed.). Vilamoura, Portugal: SciTePress, p. 407 - 412

    Publication: Chapter in book/Conference proceedingContribution to conference proceedings

    Open Access
    File
    1 Downloads (Pure)
  • Computing Semantic Association: Comparing Spreading Activation and Spectral Association for Ontology Learning

    Wohlgenannt, G., Belk, S. & Schett, M., 1 Dec 2013, Computing Semantic Association: Comparing Spreading Activation and Spectral Association for Ontology Learning. Ramanna, S., Lingras, P., Sombattheera, C., Krishna, A. (eds.), MIWAI, Lecture Notes in Computer Science (LNCS) 8271 (ed.). Krabi, Thailand: Springer, p. 317 - 328

    Publication: Chapter in book/Conference proceedingContribution to conference proceedings

    Open Access
    File
    1 Downloads (Pure)
  • Confidence Management for Learning Ontologies from Dynamic Web Sources

    Wohlgenannt, G., Weichselbraun, A., Scharl, A. & Sabou, M., 1 Oct 2012, 4th International Conference on Knowledge Engineering and Ontology Development (KEOD-2012). Joaquim Filipe and Jan Dietz (ed.). Barcelona, Spain: SciTePress, p. 172 - 177

    Publication: Chapter in book/Conference proceedingContribution to conference proceedings