The rapidly growing volume of scientific publications offers an interesting challenge for research on methods for analyzing the authorship of documents with one or more authors. However, most existing datasets lack scientific documents or the necessary metadata for constructing new experiments and test cases. We introduce SMAuC, a comprehensive, metadata-rich corpus tailored to scientific authorship analysis. Comprising over 3 million publications across various disciplines from over 5 million authors, SMAuC is the largest openly accessible corpus for this purpose. It encompasses scientific texts from humanities and natural sciences, accompanied by extensive, curated metadata, including unambiguous author IDs. SMAuC aims to significantly advance the domain of authorship analysis in scientific texts.
%0 Journal Article
%1 Bevendorff2022-qf
%A Bevendorff, Janek
%A Sauer, Philipp
%A Gienapp, Lukas
%A Kircheis, Wolfgang
%A Körner, Erik
%A Stein, Benno
%A Potthast, Martin
%D 2022
%I arXiv
%K
%T SMAuC -- the scientific multi-authorship corpus
%X The rapidly growing volume of scientific publications offers an interesting challenge for research on methods for analyzing the authorship of documents with one or more authors. However, most existing datasets lack scientific documents or the necessary metadata for constructing new experiments and test cases. We introduce SMAuC, a comprehensive, metadata-rich corpus tailored to scientific authorship analysis. Comprising over 3 million publications across various disciplines from over 5 million authors, SMAuC is the largest openly accessible corpus for this purpose. It encompasses scientific texts from humanities and natural sciences, accompanied by extensive, curated metadata, including unambiguous author IDs. SMAuC aims to significantly advance the domain of authorship analysis in scientific texts.
@article{Bevendorff2022-qf,
abstract = {The rapidly growing volume of scientific publications offers an interesting challenge for research on methods for analyzing the authorship of documents with one or more authors. However, most existing datasets lack scientific documents or the necessary metadata for constructing new experiments and test cases. We introduce SMAuC, a comprehensive, metadata-rich corpus tailored to scientific authorship analysis. Comprising over 3 million publications across various disciplines from over 5 million authors, SMAuC is the largest openly accessible corpus for this purpose. It encompasses scientific texts from humanities and natural sciences, accompanied by extensive, curated metadata, including unambiguous author IDs. SMAuC aims to significantly advance the domain of authorship analysis in scientific texts.},
added-at = {2024-09-10T10:41:24.000+0200},
author = {Bevendorff, Janek and Sauer, Philipp and Gienapp, Lukas and Kircheis, Wolfgang and K{\"o}rner, Erik and Stein, Benno and Potthast, Martin},
biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/2b2d2f49caaf0560473dbbd2ba0b0f5cb/scadsfct},
interhash = {43438da40cac33cd7fc1ff6374f93bee},
intrahash = {b2d2f49caaf0560473dbbd2ba0b0f5cb},
keywords = {},
publisher = {arXiv},
timestamp = {2024-09-10T10:47:32.000+0200},
title = {{SMAuC} -- the scientific multi-authorship corpus},
year = 2022
}
