@MastersThesis{laitio_masters_thesis,
  author =   {Joonas Laitio},
  title =    {Semantic Web Data Quality Control},
  school =   {Aalto University, School of Electrical Engineering, Degree Programme of Automation and Systems Technology},
  year =     {2011},
  month =    {October},
  abstract = {Data quality is a growing concern on the Semantic Web. The amount of data
available is growing faster than ever, and the emphasis thus far has been on
creating and interlinking data without much regard to how good the data actually
is. The trend is shifting from creating new data to refining what already
exists.

Data quality is a subjective concept and a formal representation for it is often
troublesome. First, we must define what is meant by data quality - what are the
different facets of the concept. Second, a way for representing this quality
must be found. Third, actual processes to refine data and improve its quality
and ways to take data quality into account on the Semantic Web
must be developed.  

This work presents some solutions to the problem. Many ways to annotate quality
metadata as RDF are first discovered, along with their pros and cons. A
framework for managing RDF-based quality metadata is presented,
with a set of tools for specifically managing the quality annotations. Additionally,
an automatic annotation system and a schema validation system, within the
restraints of the open world assumption, have been designed, implemented and
integrated into the framework. The system has been tested using real life
datasets with promising first results.
},
  OPTannotate = {semantic web, ontologies, data creation, validation, data quality},
  OPTproject =   {http://www.seco.tkk.fi/projects/finnonto}
}