Effects of a Machine Learning-empowered Chinese Character Handwriting Learning Tool on Rectifying Legible Writing in Young Children: A Pilot Study

Abstract

The logographic nature of Chinese script is a major dissuading factor for learning handwriting. The challenge is the complex psycholinguistic process behind handwriting. Thus, we developed AI-Strokes, a Chinese handwriting learning tool that assists teachers in facilitating students’ handwriting practice in various modalities, and provides personalized feedback for the students. By leveraging a trainable Machine Learning back-end framework, the tool diagnoses and scores students’ handwriting errors. This paper reports a pilot study in a Singapore primary school with an early prototype of AI-Strokes. Two classes of students went through AI-Strokes-based Chinese handwriting lessons (the experimental group) and conventional lessons (the control group) respectively. Pre- and post-tests were administered, and their handwriting processes were analyzed regarding errors in stroke orders, extra/missing strokes, and errors in stroke directions. The results show that the experimental group has yielded significantly better learning gains than the control group. It is posited that the personalized feedback of AI-Strokes has formed a feedback loop to support students’ trial-and-error process in improving their handwriting skills. The multimodal handwriting task design may have also fostered their orthographic awareness through the activation of alternative psycholinguistic pathways during their handwriting lessons.