AI-Driven myChatCT: Enhancing Computational Thinking and Coding Skills in High School Education

Recently the education system has progressively emphasized computational thinking (CT) and coding skills. The curriculum progresses from foundational tools like Scratch in elementary education to more complex languages such as Python and C++ in senior high school. However, traditional teaching methods often fail to engage students effectively, hindering their development of critical coding skills. This research evaluates the effectiveness of myChatCT, an artificial intelligence (AI)-enabled learning assistant designed to enhance CT and coding skills among high school students. A distinctive feature of myChatCT is its integration of activity diagrams, bridging the gap between students' cognitive processes and their visual representations, along with the corresponding programming code. This not only clarifies complex concepts but also promotes deeper understanding and engagement. The study involved four distinct cohorts of high school students who completed coding tasks both with and without the assistance of myChatCT. A mixed-methods approach was employed, combining quantitative assessments of coding performance with qualitative feedback on learning experiences. The results revealed a significant improvement in performance metrics among students using myChatCT, as evidenced by higher accuracy rates and faster completion times. Qualitative feedback revealed that students felt more confident in their coding abilities and were more motivated to engage with programming concepts when supported by myChatCT. These findings underscore myChatCT's potential as a valuable educational tool that can facilitate deeper understanding and engagement in coding education, preparing high school students for a technology-driven future. By leveraging AI capabilities and visual aids, myChatCT not only enhances students' coding skills but also fosters a more interactive and supportive learning environment. This research contributes to the growing body of literature on AI application in education, emphasizing the significance of innovative pedagogical approaches in improving student learning experiences and outcomes within an evolving educational landscape. Ultimately, the integration of tools like myChatCT represents a significant step forward in addressing the challenges of traditional education, paving the way for a more effective and engaging learning experience in the digital age.

Authors

Institutions

Publication Details

Published
2025-04-22
DOI
https://doi.org/10.1109/educon62633.2025.11016419
Citations
1
Primary Topic
Online Learning and Analytics
Type
article
Field-Weighted Citation Impact
1.69
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

AI-Driven myChatCT: Enhancing Computational Thinking and Coding Skills in High School Education

Liwei Chen, Po‐Hsun Cheng, Kuan-Yeh Lin
1 citations
Online Learning and Analytics
1.69
article

AI-Driven myChatCT: Enhancing Computational Thinking and Coding Skills in High School Education

Liwei Chen, Po‐Hsun Cheng, Kuan-Yeh Lin
article en
1 citations

Abstract

Recently the education system has progressively emphasized computational thinking (CT) and coding skills. The curriculum progresses from foundational tools like Scratch in elementary education to more complex languages such as Python and C++ in senior high school. However, traditional teaching methods often fail to engage students effectively, hindering their development of critical coding skills. This research evaluates the effectiveness of myChatCT, an artificial intelligence (AI)-enabled learning assistant designed to enhance CT and coding skills among high school students. A distinctive feature of myChatCT is its integration of activity diagrams, bridging the gap between students' cognitive processes and their visual representations, along with the corresponding programming code. This not only clarifies complex concepts but also promotes deeper understanding and engagement. The study involved four distinct cohorts of high school students who completed coding tasks both with and without the assistance of myChatCT. A mixed-methods approach was employed, combining quantitative assessments of coding performance with qualitative feedback on learning experiences. The results revealed a significant improvement in performance metrics among students using myChatCT, as evidenced by higher accuracy rates and faster completion times. Qualitative feedback revealed that students felt more confident in their coding abilities and were more motivated to engage with programming concepts when supported by myChatCT. These findings underscore myChatCT's potential as a valuable educational tool that can facilitate deeper understanding and engagement in coding education, preparing high school students for a technology-driven future. By leveraging AI capabilities and visual aids, myChatCT not only enhances students' coding skills but also fosters a more interactive and supportive learning environment. This research contributes to the growing body of literature on AI application in education, emphasizing the significance of innovative pedagogical approaches in improving student learning experiences and outcomes within an evolving educational landscape. Ultimately, the integration of tools like myChatCT represents a significant step forward in addressing the challenges of traditional education, paving the way for a more effective and engaging learning experience in the digital age.

National Kaohsiung Normal University (TW)
Quality Education
Openalex Percentile: Top 13%
Online Learning and Analytics
1.69
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.