Kanji Workbook: A Writing-Based Intelligent Tutoring System for Learning Proper Japanese Kanji Writing Technique with Instructor-Emulated Assessment

TL;DR

Kanji Workbook introduces a writing-based intelligent tutoring system that provides instructor-emulated feedback for kanji writing. It combines a rich ten-metric assessment framework with expert templates and a teacher-inspired user interface to deliver granular feedback on structure, technique, and precision. Across nine months of classroom deployment with 94 students, the system yielded statistically significant improvements in mean scores and received positive qualitative feedback, while also revealing areas for visual fidelity and assessment refinement. The work demonstrates the practical potential of instructor-like feedback in scalable kanji learning and sets the stage for broader adaptation to related languages and curricula.

Abstract

Kanji script writing is a skill that is often introduced to novice Japanese foreign language students for achieving Japanese writing mastery, but often poses difficulties to students with primarily English fluency due to their its vast differences with written English. Instructors often introduce various pedagogical methods -- such as visual structure and written techniques -- to assist students in kanji study, but may lack availability providing direct feedback on students' writing outside of class. Current educational applications are also limited due to lacking richer instructor-emulated feedback. We introduce Kanji Workbook, a writing-based intelligent tutoring system for students to receive intelligent assessment that emulates human instructor feedback. Our interface not only leverages students' computing devices for allowing them to learn, practice, and review the writing of prompted characters from their course's kanji script lessons, but also provides a diverse set of writing assessment metrics -- derived from instructor interviews and classroom observation insights -- through intelligent scoring and visual animations. We deployed our interface onto novice- and intermediate-level university courses over an entire academic year, and observed that interface users on average achieved higher course grades than their peers and also reacted positively to our interface's various features.

Figures (10)

• Figure 1: Structure assessment visualizations for: stroke match (left), stroke valid (middle), and stroke exist (right).
• Figure 2: Technique assessment visualizations for: stroke order (left) and stroke direction (right).
• Figure 3: Precision assessment visualizations for: stroke length (left) and stroke closeness (right).
• Figure 4: Subset of characters in Kanji Workbook.
• Figure 5: Practice mode view.