@inproceedings{Suchomel2017,
  author    = {V{\´i}t Suchomel},
  title     = {Removing spam from web corpora through supervised learning using FastText},
  series = {Proceedings of the Workshop on Challenges in the Management of Large Corpora and Big Data and Natural Language Processing (CMLC-5+BigNLP) 2017 including the papers from the Web-as-Corpus (WAC-XI) guest section. Birmingham, 24 July 2017},
  editor    = {Piotr Bański and Marc Kupietz and Harald L{\"u}ngen and Paul Rayson and Hanno Biber and Evelyn Breiteneder and Simon Clematide and John Mariani and Mark Stevenson and Theresa Sick},
  publisher = {Institut f{\"u}r Deutsche Sprache},
  address   = {Mannheim},
  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-62674},
  pages     = {56 -- 60},
  year      = {2017},
  abstract  = {Unlike traditional text corpora collected from trustworthy sources, the content of web based corpora has to be filtered. This study briefly discusses the impact of web spam on corpus usability and emphasizes the importance of removing computer generated text from web corpora. The paper also presents a keyword comparison of an unfiltered corpus with the same collection of texts cleaned by a supervised classifier trained using FastText. The classifier was able to recognize 71\% of web spam documents similar to the training set but lacked both precision and recall when applied to short texts from another data set.},
  language  = {en}
}