Logo image
Automatically Assess Elementary Students' Hand-Drawn Scientific Models Using Deep Learning of Artificial Intelligence
Conference poster   Open access

Automatically Assess Elementary Students' Hand-Drawn Scientific Models Using Deep Learning of Artificial Intelligence

Tingting Li, Feng Liu and Joseph Krajcik
ISLS Annual Meeting 2023: Building Knowledge and Sustaining our Community - 17th International Conference of the Learning Sciences, ICLS 2023, Proceedings, pp 1813-1814
2023
url
https://doi.org/10.22318/icls2023.933529View
Published, Version of Record (VoR) Open Open Access (License Unspecified)

Abstract

Because of the complexity of scoring open-end tasks, machine learning (ML) has been utilized for automatically assessing students' constructed responses. However, most existing research focuses on grading text-based responses. No studies have investigated the automatic scoring of hand-drawn models created by elementary students. In this study, we applied ML to automatically score hand-drawn scientific models developed by elementary students for evaluating knowledge-in-use. We first developed algorithms using human-scored responses and then validated these algorithms with new data. We also implemented a data augmentation technique to enhance accuracy. Our findings demonstrate the potential of the developed algorithm to achieve high performance in automatically scoring hand-drawn models.

Metrics

6 Record Views

Details

Logo image