The paper "Improving Students' Argumentation Skills Using Dynamic Machine Learning (ML)-based Modeling" by Thiemo Wambsganß, Andreas Janson, Matthias Söllner, Ken Koedinger and Jan Marco Leimeister has been accepted for publication in the journal Information Systems Research (ISR). The Information System Research Journal is one of the most important journals in the field of information systems.

In the article, the authors examine how students' reasoning skills, especially strategic decision making and persuasion, can be improved through the use of machine learning. The authors address the challenge of providing scalable and personalized feedback to improve these skills. In the study, machine learning (ML) is used to provide scalable, immediate feedback, which is of great importance for educational innovation and practice.

A dynamic ML-based system was developed and tested in three empirical studies in comparison to traditional scripted and adaptive supports. This methodological approach makes it possible to evaluate the effectiveness of dynamic modeling to improve reasoning ability.

The results show that the dynamic system significantly improves learners' objective reasoning skills across different tasks and proficiency levels and outperforms traditional methods. It proves effective in both complex and simple reasoning tasks and provides robust support tailored to learners' individual needs.

The research contributes to new knowledge by demonstrating the effectiveness of dynamic ML-based modeling outside of traditional STEM domains in areas such as persuasive writing. This highlights the potential of adaptive learning technologies to transform educational practice and policy by promoting critical thinking and communication skills.

The paper can be viewed at the following link: https://pubsonline.informs.org/doi/10.1287/isre.2021.0615