@misc{PUB-0027,
  title = {{Building a DDC-annotated Corpus from OAI Metadata}},
  author = {Lösch, M. and Waltinger, U. and Horstmann, W. and Mehler, A.},
  year = {2011},
  url = {https://jodi-ojs-tdl.tdl.org/jodi/article/view/1765},
  abstract = {Document servers complying to the standards of the Open Archives Initiative (OAI) are rich,
yet seldom exploited source of textual primary data for research fields in text mining,
natural language processing or computational linguistics. We present a bilingual (English and
German) text corpus consisting of bibliographic OAI records and the associated full texts. A
particular added value is that we annotated each record with at least one Dewey Decimal
Classification (DDC) number, inducing a subject-based categorization of the corpus. By this
means, it can be used as training data for machine learning-based text categorization tasks in
digital libraries, but also as primary data source for linguistic research on academic
language use related to specific disciplines. We describe the construction of the corpus using
data from the Bielefeld Academic Search Engine (BASE), as well as its characteristics.},
  note = {Lösch, M., Waltinger, U., Horstmann, W., \& Mehler, A. (2011). Building a DDC-annotated Corpus from OAI Metadata. Journal of Digital Information, 12(2).}
}