Development of an Unsupervised LearningBased Automated Evaluation System of Descriptive Assessment

Abstract

Current research on automatic scoring using traditional supervised learning methodscannot grade responses to questions that are newly generated or created spontaneously. Additionally, relying on pre-developed questions and their corresponding scoring modelsfor lesson planning may limit the creativity and diversity of instruction. This study proposesa method that can quickly evaluate student responses and generate feedback withoutthe need for pre-developed models. We introduces the SAAI system, which employsunsupervised learning techniques to instantly create scoring models based on studentresponses, thereby generating evaluation and feedback information. The SAAI systemcomplements the automatic scoring of traditional supervised learning methods andsupports scoring for a wide range of newly generated questions. This research elucidates theprinciples and significance of this system.