An AI-Based Commentary Function with Estimated State Rating Framework for Student Learning Support in Java Programming Learning Assistant System

As Java remains a widely used object-oriented programming language in various application systems, we have developed the Java Programming Learning Assistant System (JPLAS) to support novice learners in their self-studies. JPLAS provides a variety of exercise problems that have different learning goals and difficulties. Among them, Grammar-Concept Understanding Problems (GUP) is designed as the first step problem where key grammar concepts appearing in a given source code are questioned. In this paper, we propose a commentary function supported by generative AI for GUP to study challenging concepts of Java programming such as generics and lambda expressions. This function provides AI-generated four-level hints to help students solve given questions. Besides, the Estimated State Rating (ESR) framework is presented to numerically describe the learning stagnation of a student. ESR is calculated using the time interval elapsed from the previous hint access and the current answer accuracy. For evaluations, we assigned the 10 GUP instances with the commentary function to 33 students in Okayama University, Japan, and calculated ESR from their log data. The evaluation examines the ESR values associated with the first recorded access to each commentary function and derives the corresponding 75th percentile as a reasonable reference threshold to allow the next-level hint. In future work, we will apply the proposal to other students and examine the effects on their problem solving and learning outcomes.

Authors

Institutions

Publication Details

Journal
Electronics
Published
2026-11-13
DOI
https://doi.org/10.3390/electronics15225277
Primary Topic
Teaching and Learning Programming
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

An AI-Based Commentary Function with Estimated State Rating Framework for Student Learning Support in Java Programming Learning Assistant System

Yanhui Jing, Huiyu Qi, Mustika Mentari, Nobuo Funabiki et al.
2 links
Electronics
Teaching and Learning Programming
article

An AI-Based Commentary Function with Estimated State Rating Framework for Student Learning Support in Java Programming Learning Assistant System

Yanhui Jing, Huiyu Qi, Mustika Mentari, Nobuo Funabiki, Htoo Htoo Sandi Kyaw
article en

Abstract

As Java remains a widely used object-oriented programming language in various application systems, we have developed the Java Programming Learning Assistant System (JPLAS) to support novice learners in their self-studies. JPLAS provides a variety of exercise problems that have different learning goals and difficulties. Among them, Grammar-Concept Understanding Problems (GUP) is designed as the first step problem where key grammar concepts appearing in a given source code are questioned. In this paper, we propose a commentary function supported by generative AI for GUP to study challenging concepts of Java programming such as generics and lambda expressions. This function provides AI-generated four-level hints to help students solve given questions. Besides, the Estimated State Rating (ESR) framework is presented to numerically describe the learning stagnation of a student. ESR is calculated using the time interval elapsed from the previous hint access and the current answer accuracy. For evaluations, we assigned the 10 GUP instances with the commentary function to 33 students in Okayama University, Japan, and calculated ESR from their log data. The evaluation examines the ESR values associated with the first recorded access to each commentary function and derives the corresponding 75th percentile as a reasonable reference threshold to allow the next-level hint. In future work, we will apply the proposal to other students and examine the effects on their problem solving and learning outcomes.

ElectronicsVol. 15(22)
Okayama University (JP)
Quality education
Teaching and Learning Programming
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon