Affiliations: University of Ljubljana, Faculty of Computer and Information Science, Večna pot 113, Ljubljana, Slovenia. [email protected], [email protected]
Correspondence:
[*]
University of Ljubljana, Faculty of Computer and Information Science, Večna pot 113, Ljubljana, Slovenia
Abstract: Automated essay evaluation is a widely used practical solution for replacing time-consuming manual grading of student essays. Automated systems are used in combination with human graders in different high-stake assessments, where grading models are learned on essays datasets scored by different graders. Despite the definition of the standardized grading rules, human graders can unintentionally introduce subjective bias into scores. Consequently, a grading model has to learn from data that represents a noisy relationship between essay attributes and its grade. We propose an approach for partitioning a set of essays into subsets that represent similar graders, which uses an explanation methodology and clustering. The results confirm our assumption that learning from the ensemble of separated models can significantly improve the average prediction accuracy on artificial and real-world datasets.
Keywords: automated essay evaluation, explanations of predictions, clustering, PCA
