@inproceedings{SuarezKarlovaBourbonusLobin2018,
  author    = {Holger Grumt Suarez and Natali Karlova-Bourbonus and Henning Lobin},
  title     = {A Discourse-structured Blog Corpus for German: Challenges of Compilation and Annotation},
  series = {NLP4CMC III: 3rd Workshop on Natural Language Processing for Computer-Mediated Communication. 22 September 2016},
  editor    = {Michael Bei{\"s}wenger and Michael Wojatzki and Torsten Zesch},
  publisher = {Ruhr-Universit{\"a}t Bochum, Sprachwissenschaftliches Institut},
  address   = {Bochum},
  issn      = {2190-0949},
  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-75810},
  pages     = {1 -- 5},
  year      = {2018},
  abstract  = {The present paper reports the first results of the compilation and annotation of a blog corpus for German. The main aim of the project is the representation of the blog discourse structure and relations between its elements (blog posts, comments) and participants (bloggers, commentators). The data included in the corpus were manually collected from the scientific blog portal SciLogs. The feature catalogue for the corpus annotation includes three types of information which is directly or indirectly provided in the blog or can be construed by means of statistical analysis or computational tools. At this point, only directly available information (e.g. title of the blog post, name of the blogger etc.) has been annotated. We believe, our blog corpus can be of interest for the general study of blog structure or related research questions as well as for the development of NLP methods and techniques (e.g. for authorship detection).},
  language  = {en}
}