@inproceedings{FreyerThewesMeinecke2023,
  author    = {Freyer, Nils and Thewes, Dustin and Meinecke, Matthias},
  title     = {GUIDO: a hybrid approach to guideline discovery \& ordering from natural language texts},
  series = {Proceedings of the 12th International Conference on Data Science, Technology and Applications DATA - Volume 1},
  booktitle = {Proceedings of the 12th International Conference on Data Science, Technology and Applications DATA - Volume 1},
  editor    = {Gusikhin, Oleg and Hammoudi, Slimane and Cuzzocrea, Alfredo},
  isbn      = {978-989-758-664-4},
  issn      = {2184-285X},
  doi       = {10.5220/0012084400003541},
  pages     = {335 -- 342},
  year      = {2023},
  abstract  = {Extracting workflow nets from textual descriptions can be used to simplify guidelines or formalize textual descriptions of formal processes like business processes and algorithms. The task of manually extracting processes, however, requires domain expertise and effort. While automatic process model extraction is desirable, annotating texts with formalized process models is expensive. Therefore, there are only a few machine-learning-based extraction approaches. Rule-based approaches, in turn, require domain specificity to work well and can rarely distinguish relevant and irrelevant information in textual descriptions. In this paper, we present GUIDO, a hybrid approach to the process model extraction task that first, classifies sentences regarding their relevance to the process model, using a BERT-based sentence classifier, and second, extracts a process model from the sentences classified as relevant, using dependency parsing. The presented approach achieves significantly better resul ts than a pure rule-based approach. GUIDO achieves an average behavioral similarity score of 0.93. Still, in comparison to purely machine-learning-based approaches, the annotation costs stay low.},
  language  = {en}
}
@article{BensbergAuthCzarnecki2020,
  author    = {Bensberg, Frank and Auth, Gunnar and Czarnecki, Christian},
  title     = {Literaturanalyse mit Text Mining},
  series = {E-Learning and Education (eleed)},
  journal   = {E-Learning and Education (eleed)},
  number    = {13},
  editor    = {Haake, J{\"o}rg M.},
  publisher = {FernUniversit{\"a}t in Hagen},
  address   = {Hagen},
  issn      = {1860-7470},
  pages     = {1 -- 13},
  year      = {2020},
  abstract  = {Die Durchf{\"u}hrung einer systematischen Literaturrecherche ist eine zentrale Kompetenz wissenschaftlichen Arbeitens und bildet daher einen festen Ausbildungsbestandteil von Bachelor- und Masterstudieng{\"a}ngen. In entsprechenden Lehrveranstaltungen werden Studierende zwar mit den grundlegenden Hilfsmitteln zur Suche und Verwaltung von Literatur vertraut gemacht, allerdings werden die Potenziale textanalytischer Methoden und Anwendungssysteme (Text Mining, Text Analytics) dabei zumeist nicht abgedeckt. Folglich werden Datenkompetenzen, die zur systemgest{\"u}tzten Analyse und Erschließung von Literaturdaten erforderlich sind, nicht hinreichend ausgepr{\"a}gt. Um diese Kompetenzl{\"u}cke zu adressieren, ist an der Hochschule Osnabr{\"u}ck eine Lehrveranstaltung konzipiert und projektorientiert umgesetzt worden, die sich insbesondere an Studierende wirtschaftswissenschaftlicher Studieng{\"a}nge richtet. Dieser Beitrag dokumentiert die fachliche sowie technische Ausgestaltung dieser Veranstaltung und zeigt Potenziale f{\"u}r die k{\"u}nftige Weiterentwicklung auf.},
  language  = {de}
}
@inproceedings{BuesgenKloeserKohletal.2022,
  author    = {B{\"u}sgen, Andr{\´e} and Kl{\"o}ser, Lars and Kohl, Philipp and Schmidts, Oliver and Kraft, Bodo and Z{\"u}ndorf, Albert},
  title     = {Exploratory analysis of chat-based black market profiles with natural language processing},
  series = {Proceedings of the 11th International Conference on Data Science, Technology and Applications},
  booktitle = {Proceedings of the 11th International Conference on Data Science, Technology and Applications},
  isbn      = {978-989-758-583-8},
  issn      = {2184-285X},
  doi       = {10.5220/0011271400003269},
  pages     = {83 -- 94},
  year      = {2022},
  abstract  = {Messenger apps like WhatsApp or Telegram are an integral part of daily communication. Besides the various positive effects, those services extend the operating range of criminals. Open trading groups with many thousand participants emerged on Telegram. Law enforcement agencies monitor suspicious users in such chat rooms. This research shows that text analysis, based on natural language processing, facilitates this through a meaningful domain overview and detailed investigations. We crawled a corpus from such self-proclaimed black markets and annotated five attribute types products, money, payment methods, user names, and locations. Based on each message a user sends, we extract and group these attributes to build profiles. Then, we build features to cluster the profiles. Pretrained word vectors yield better unsupervised clustering results than current state-of-the-art transformer models. The result is a semantically meaningful high-level overview of the user landscape of black market chatrooms. Additionally, the extracted structured information serves as a foundation for further data exploration, for example, the most active users or preferred payment methods.},
  language  = {en}
}