Paper Number



Education is increasingly being delivered digitally these days, whether due to the COVID-19 pandemic or the growing popularity of MOOCs. The increasing number of participants poses a challenge for institutions to balance didactical and financial demands, especially for exams. The overall goal of this design science research project is to design and evaluate a semi-automatic machine-learning-based scoring system for essays. We focus on the design of a functional software artifact including the required design principles and an exemplary implementation of an algorithm, the optimization of which is, however, not part of this project and subject for future research. Our results show that such a system is suitable for both scoring essay assignments and documenting these scorings. In addition to the software artifact, we document our results using the work of Gregor et al. (2020). This provides a first step towards a design theory for semi-automatic, machine-learning-based scoring systems for essays.



When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.