@inproceedings{Barbaresi2019,
  author    = {Adrien Barbaresi},
  title     = {The Vast and the Focused: On the need for domain-focused web corpora},
  series = {Proceedings of the Workshop on Challenges in the Management of Large Corpora (CMLC-7) 2019. Cardiff, 22nd July 2019},
  editor    = {Piotr Bański and Adrien Barbaresi and Hanno Biber and Evelyn Breiteneder and Simon Clematide and Marc Kupietz and Harald L{\"u}ngen and Caroline Iliadi},
  publisher = {Leibniz-Institut f{\"u}r Deutsche Sprache},
  address   = {Mannheim},
  doi       = {10.14618/ids-pub-9025},
  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-90257},
  pages     = {29 -- 32},
  year      = {2019},
  abstract  = {As the Web ought to be considered as a series of sources rather than as a source in itself, a problem facing corpus construction resides in meta-information and categorization. In addition, we need focused data to shed light on particular subfields of the digital public sphere. Blogs are relevant to that end, especially if the resulting web texts can be extracted along with metadata and made available in coherent and clearly describable collections.},
  language  = {en}
}