@article{benellefi2017dataset,
  abstract = {The Web of Data, and in particular Linked Data, has seen tremendous growth over
the past years. However, reuse and take-up of these rich data sources is often limited and focused on a few well-known and established RDF datasets. This can be partially attributed to the lack of reliable and up-to-date information about the characteristics of available datasets. While RDF datasets vary heavily with respect to the features related to quality, provenance, interlinking, licenses, statistics and dynamics, reliable information about such features is essential to enable dataset discovery and selection in tasks such as entity linking, distributed
query, search or question answering. Even though there exists a wealth of works contributing to the task of dataset profiling in general, these works are spread across a wide range of communities. In this survey, we provide a first comprehensive overview of the RDF dataset profiling features, methods, tools and vocabularies. We organize these building blocks of dataset profiling in a taxonomy and illustrate the links between the dataset profiling and feature extraction approaches and several application domains. This survey is aimed towards data practitioners, data providers and
scientists, spanning a large range of communities and drawing from different fields such as dataset profiling, assessment, summarization and characterization. Ultimately, this work is intended to facilitate the reader to identify the relevant features for building a dataset profile for intended applications together with the methods and tools capable of extracting these features from the datasets as well as vocabularies to describe the extracted features and make them available.},
  added-at = {2018-01-24T13:16:22.000+0100},
  author = {Ben Ellefi, Mohamed and Bellahsene, Zohra and John, Breslin and Demidova, Elena and Dietze, Stefan and Szymanski, Julian and Todorov, Konstantin},
  biburl = {https://www.bibsonomy.org/bibtex/2cbe8190aa5a8583646b2a3554ad813c6/alexandriaproj},
  interhash = {1da8a6614f9be80ffb0dcdc2253e928a},
  intrahash = {cbe8190aa5a8583646b2a3554ad813c6},
  journal = {Semantic Web Journal},
  keywords = {alexandria wikipedia},
  note = {accepted in August 2017, to appear.},
  timestamp = {2018-01-24T13:16:22.000+0100},
  title = {RDF Dataset Profiling - a Survey of Features, Methods, Vocabularies and Applications},
  url = {http://www.semantic-web-journal.net/content/rdf-dataset-profiling-survey-features-methods-vocabularies-and-applications},
  year = 2017
}

@article{benellefi2017dataset,
  abstract = {The Web of Data, and in particular Linked Data, has seen tremendous growth over
the past years. However, reuse and take-up of these rich data sources is often limited and focused on a few well-known and established RDF datasets. This can be partially attributed to the lack of reliable and up-to-date information about the characteristics of available datasets. While RDF datasets vary heavily with respect to the features related to quality, provenance, interlinking, licenses, statistics and dynamics, reliable information about such features is essential to enable dataset discovery and selection in tasks such as entity linking, distributed
query, search or question answering. Even though there exists a wealth of works contributing to the task of dataset profiling in general, these works are spread across a wide range of communities. In this survey, we provide a first comprehensive overview of the RDF dataset profiling features, methods, tools and vocabularies. We organize these building blocks of dataset profiling in a taxonomy and illustrate the links between the dataset profiling and feature extraction approaches and several application domains. This survey is aimed towards data practitioners, data providers and
scientists, spanning a large range of communities and drawing from different fields such as dataset profiling, assessment, summarization and characterization. Ultimately, this work is intended to facilitate the reader to identify the relevant features for building a dataset profile for intended applications together with the methods and tools capable of extracting these features from the datasets as well as vocabularies to describe the extracted features and make them available.},
  added-at = {2017-11-13T07:14:25.000+0100},
  author = {Ben Ellefi, Mohamed and Bellahsene, Zohra and John, Breslin and Demidova, Elena and Dietze, Stefan and Szymanski, Julian and Todorov, Konstantin},
  biburl = {https://www.bibsonomy.org/bibtex/2cbe8190aa5a8583646b2a3554ad813c6/dietze},
  interhash = {1da8a6614f9be80ffb0dcdc2253e928a},
  intrahash = {cbe8190aa5a8583646b2a3554ad813c6},
  journal = {Semantic Web Journal},
  keywords = {AFEL data4urbanmobility l3s myown sysrelevantforl3s},
  note = {accepted in August 2017, to appear.},
  timestamp = {2017-11-13T07:14:25.000+0100},
  title = {RDF Dataset Profiling - a Survey of Features, Methods, Vocabularies and Applications},
  url = {http://www.semantic-web-journal.net/content/rdf-dataset-profiling-survey-features-methods-vocabularies-and-applications},
  year = 2017
}