@phdthesis{Abedjan2014,
  author    = {Abedjan, Ziawasch},
  title     = {Improving RDF data with data mining},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-71334},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {Linked Open Data (LOD) comprises very many and often large public data sets and knowledge bases. Those datasets are mostly presented in the RDF triple structure of subject, predicate, and object, where each triple represents a statement or fact. Unfortunately, the heterogeneity of available open data requires significant integration steps before it can be used in applications. Meta information, such as ontological definitions and exact range definitions of predicates, are desirable and ideally provided by an ontology. However in the context of LOD, ontologies are often incomplete or simply not available. Thus, it is useful to automatically generate meta information, such as ontological dependencies, range definitions, and topical classifications. Association rule mining, which was originally applied for sales analysis on transactional databases, is a promising and novel technique to explore such data. We designed an adaptation of this technique for min-ing Rdf data and introduce the concept of "mining configurations", which allows us to mine RDF data sets in various ways. Different configurations enable us to identify schema and value dependencies that in combination result in interesting use cases. To this end, we present rule-based approaches for auto-completion, data enrichment, ontology improvement, and query relaxation. Auto-completion remedies the problem of inconsistent ontology usage, providing an editing user with a sorted list of commonly used predicates. A combination of different configurations step extends this approach to create completely new facts for a knowledge base. We present two approaches for fact generation, a user-based approach where a user selects the entity to be amended with new facts and a data-driven approach where an algorithm discovers entities that have to be amended with missing facts. As knowledge bases constantly grow and evolve, another approach to improve the usage of RDF data is to improve existing ontologies. Here, we present an association rule based approach to reconcile ontology and data. Interlacing different mining configurations, we infer an algorithm to discover synonymously used predicates. Those predicates can be used to expand query results and to support users during query formulation. We provide a wide range of experiments on real world datasets for each use case. The experiments and evaluations show the added value of association rule mining for the integration and usability of RDF data and confirm the appropriateness of our mining configuration methodology.},
  language  = {en}
}
@phdthesis{Lorey2014,
  author    = {Lorey, Johannes},
  title     = {What's in a query : analyzing, predicting, and managing linked data access},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus-72312},
  school      = {Universit{\"a}t Potsdam},
  year      = {2014},
  abstract  = {The term Linked Data refers to connected information sources comprising structured data about a wide range of topics and for a multitude of applications. In recent years, the conceptional and technical foundations of Linked Data have been formalized and refined. To this end, well-known technologies have been established, such as the Resource Description Framework (RDF) as a Linked Data model or the SPARQL Protocol and RDF Query Language (SPARQL) for retrieving this information. Whereas most research has been conducted in the area of generating and publishing Linked Data, this thesis presents novel approaches for improved management. In particular, we illustrate new methods for analyzing and processing SPARQL queries. Here, we present two algorithms suitable for identifying structural relationships between these queries. Both algorithms are applied to a large number of real-world requests to evaluate the performance of the approaches and the quality of their results. Based on this, we introduce different strategies enabling optimized access of Linked Data sources. We demonstrate how the presented approach facilitates effective utilization of SPARQL endpoints by prefetching results relevant for multiple subsequent requests. Furthermore, we contribute a set of metrics for determining technical characteristics of such knowledge bases. To this end, we devise practical heuristics and validate them through thorough analysis of real-world data sources. We discuss the findings and evaluate their impact on utilizing the endpoints. Moreover, we detail the adoption of a scalable infrastructure for improving Linked Data discovery and consumption. As we outline in an exemplary use case, this platform is eligible both for processing and provisioning the corresponding information.},
  language  = {en}
}