Comparison of Dimension Reduction Methods for Automated Essay Grading
Tuomo Kakkonen
Department of Computer Science and Statistics, University of Joensuu, Finland
Niko Myller
Department of Computer Science and Statistics, University of Joensuu, Finland // niko.myller@cs.joensuu.fi // Tel. +358 13 251 7929 // Fax. +358 13 251 7955
Erkki Sutinen
Department of Computer Science and Statistics, University of Joensuu, Finland
Jari Timonen
Department of Computer Science and Statistics, University of Joensuu, Finland
ABSTRACT: Automatic Essay Assessor (AEA) is a system that utilizes information retrieval techniques such as Latent Semantic Analysis (LSA), Probabilistic Latent Semantic Analysis (PLSA), and Latent Dirichlet Allocation (LDA) for automatic essay grading. The system uses learning materials and relatively few teacher-graded essays for calibrating the scoring mechanism before grading. We performed a series of experiments using LSA, PLSA and LDA for document comparisons in AEA. In addition to comparing the methods on a theoretical level, we compared the applicability of LSA, PLSA, and LDA to essay grading with empirical data. The results show that the use of learning materials as training data for the grading model outperforms the k-NN-based grading methods. In addition to this, we found that using LSA yielded slightly more accurate grading than PLSA and LDA. We also found that the division of the learning materials in the training data is crucial. It is better to divide learning materials into sentences than paragraphs.
Keywords: Automatic essay grading, Dimensionality reduction, Latent semantic analysis, Probabilistic latent semantic analysis, Latent Dirichlet allocation
[277 Kb]