@article{60472,
  abstract     = {{Der Beitrag beschäftigt sich mit der didaktischen Modellierung automatisierten adaptiven Feedbacks
zu argumentativen Lerner*innentexten. An einem Korpus aus diesen Texten wird gezeigt, wie adap-
tives Feedback auf Grundlage einer Mehrebenenannotation, einem mehrdimensionalen Qualitäts-
rating und Varianzanalysen modelliert werden kann. Im Beitrag wird zunächst ein Überblick über
computergestützte Unterstützungssysteme zum Argumentieren gegeben und anschließend die An-
notation und das Rating des Korpus beleuchtet. Daran anknüpfend wird das Feedbackverständnis
dargelegt, das den Ausgangspunkt für die Modellierung des Feedbacks bildet. Die Ergebnisse der
Varianzanalysen zeigen exemplarisch, welche argumentativen Textstrukturen typisch für eine be-
stimmte Qualitätsstufe von Texten sind und indizieren damit, ab welcher Qualitätsstufe zu welchen
Kategorien Feedback gegeben werden sollte.}},
  author       = {{Rezat, Sara and Kilsbach, Sebastian and Karabey, Rabia and Michel, Nadine and Stahl, Maja  and Wachsmuth, Henning }},
  journal      = {{Leseräume: Zeitschrift für Literalität in Schule und Forschung}},
  pages        = {{1--15}},
  title        = {{{Didaktische Modellierung automatisierten adaptiven Feedbacks zu argumentativen Lerner*innentexten}}},
  doi          = {{https://leseräume.de/wp-content/uploads/2025/06/Rezat-et-al-2025-LR-JG12-H11.pdf}},
  volume       = {{11}},
  year         = {{2025}},
}

@article{58895,
  author       = {{Rezat, Sara and Kilsbach, Sebastian and Michel, Nadine and Karabey, Rabia and Stahl, Maja and Wachsmuth, Henning }},
  journal      = {{Zeitschrift für Angewandte Linguistik}},
  number       = {{82}},
  pages        = {{1--28}},
  publisher    = {{de Gruyter}},
  title        = {{{Mehrebenenannotation argumentativer Lerner*innentexte für die automatische Textauswertung}}},
  doi          = {{https://doi.org/10.1515/zfal-2025-2003}},
  year         = {{2025}},
}

@inproceedings{54513,
  abstract     = {{Learning argumentative writing is challenging. Besides writing fundamentals such as syntax and grammar, learners must select and arrange argument components meaningfully to create high-quality essays. To support argumentative writing computationally, one step is to mine the argumentative structure. When combined with automatic essay scoring, interactions of the argumentative structure and quality scores can be exploited for comprehensive writing support. Although studies have shown the usefulness of using information about the argumentative structure for essay scoring, no argument mining corpus with ground-truth essay quality annotations has been published yet. Moreover, none of the existing corpora contain essays written by school students specifically. To fill this research gap, we present a German corpus of 1,320 essays from school students of two age groups. Each essay has been manually annotated for argumentative structure and quality on multiple levels of granularity. We propose baseline approaches to argument mining and essay scoring, and we analyze interactions between both tasks, thereby laying the ground for quality-oriented argumentative writing support.}},
  author       = {{Stahl, Maja and Michel, Nadine and Kilsbach, Sebastian and Schmidtke, Julian  and Rezat, Sara and Wachsmuth, Henning}},
  keywords     = {{Annotation, Corpus, Argumentative Structure}},
  title        = {{{A School Student Essay Corpus for Analyzing Interactions of Argumentative Structure and Quality}}},
  doi          = {{10.48550/arXiv.2404.02529}},
  year         = {{2024}},
}

@inproceedings{56277,
  abstract     = {{What is learner-sensitive feedback to argumentative learner texts when it is to be issued computer- based? Learning stages are difficult to quantify. The paper provides insight into the history of research since the 1980s and a preview of what this automated feedback might look like. These questions are embedded in a research project at the Universities of Paderborn and Hannover, Germany, from which a software (project name ArgSchool) emerges that will provide such feedback.}},
  author       = {{Kilsbach, Sebastian and Michel, Nadine}},
  booktitle    = {{Proceedings of the Tenth Conference of the International Society for the Study of Argumentation}},
  keywords     = {{AI, argumentation mining, discourse history, (automated, learner-sensitive) feedback}},
  location     = {{Leiden}},
  title        = {{{Computer-Based Generation of Learner-Sensitive Feedback to Argumentative Learner Texts}}},
  year         = {{2024}},
}

@inproceedings{58899,
  author       = {{Rezat, Sara and Stahl, Maja and Michel, Nadine and Kilsbach, Sebastian and Schmidtke, Julian and Wachsmuth, Henning}},
  title        = {{{A School Student Essay Corpus for Analyzing Interactions of Argumentative Structure and Quality.}}},
  doi          = {{https://doi.org/10.48550/arXiv.2404.02529 }},
  year         = {{2024}},
}