@incollection{Cotgrove2023,
  author    = {Cotgrove, Louis},
  title     = {New opportunities for researching digital youth language: The NottDeuYTSch corpus},
  booktitle = {Neue Entwicklungen in der Korpuslandschaft der Germanistik. Beitr{\"a}ge zur IDS-Methodenmesse 2022},
  editor    = {Kupietz, Marc and Schmidt, Thomas},
  isbn      = {978-3-8233-9602-4},
  issn      = {2191-9577},
  series    = {Korpuslinguistik und interdisziplin{\"a}re Perspektiven auf Sprache | Corpus Linguistics and Interdisciplinary Perspectives on Language | CLIP},
  number    = {11},
  publisher      = {Leibniz-Institut f{\"u}r Deutsche Sprache (IDS) [Zweitver{\"o}ffentlichung]},
  pages     = {101 -- 114},
  year      = {2023},
  abstract  = {This article details the process of creating the Nottinghamer Korpus deutscher YouTube-Sprache ('The Nottingham German YouTube Language Corpus' - or NottDeuYTSch corpus) and outlines potential research opportunities. The corpus was compiled to analyse the online language produced by young German-speakers and offers significant opportunity for in-depth research across several linguistic fields including lexis, morphology, syntax, orthography, and conversational and discursive analysis. The NottDeuYTSch corpus contains over 33 million words taken from approximately 3 million YouTube comments from videos published between 2008 to 2018 targeted at a young, German-speaking demographic and represent an authentic language snapshot of young German speakers. The corpus was proportionally sampled based on video category and year from a database of 112 popular German-speaking YouTube channels in the DACH region for optimal representativeness and balance and contains a considerable amount of associated metadata for each comment that enable further longitudinal cross-sectional analyses. The NottDeuYTSch corpus is available for analysis as part of the German Reference Corpus (DeReKo).},
  subject      = {Jugendsprache},
  language  = {en}
}