GPTutor: A ChatGPT-Powered Programming Tool for Code Explanation

被引：17

作者：

Chen, Eason ^{[1
]}

Huang, Ray ^{[2
]}

Chen, Han-Shin ^{[3
]}

Tseng, Yuen-Hsien ^{[1
]}

Li, Liang-Yi ^{[1
]}

机构：

[1] Natl Taiwan Normal Univ, Taipei, Taiwan

[2] KryptoCamp, Taipei, Taiwan

[3] Univ Toronto, Toronto, ON, Canada

来源：

ARTIFICIAL INTELLIGENCE IN EDUCATION. POSTERS AND LATE BREAKING RESULTS, WORKSHOPS AND TUTORIALS, INDUSTRY AND INNOVATION TRACKS, PRACTITIONERS, DOCTORAL CONSORTIUM AND BLUE SKY, AIED 2023 | 2023年 / 1831卷

关键词：

ChatGPT; Tutoring System; Developer Tool; Prompt Engineering; Natural Language Generation;

D O I：

10.1007/978-3-031-36336-8_50

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Learning new programming skills requires tailored guidance. With the emergence of advanced Natural Language Generation models like the ChatGPT API, there is now a possibility of creating a convenient and personalized tutoring system with AI for computer science education. This paper presents GPTutor, a ChatGPT-powered programming tool, which is a Visual Studio Code extension using the ChatGPTAPI to provide programming code explanations. By integrating Visual Studio Code API, GPTutor can comprehensively analyze the provided code by referencing the relevant source codes. As a result, GPTutor can use designed prompts to explain the selected code with a pop-up message. GPTutor is now published at the Visual Studio Code Extension Marketplace, and its source code is openly accessible on GitHub. Preliminary evaluation indicates that GPTutor delivers the most concise and accurate explanations compared to vanilla ChatGPT and GitHub Copilot. Moreover, the feedback from students and teachers indicated that GPTutor is user-friendly and can explain given codes satisfactorily. Finally, we discuss possible future research directions for GPTutor. This includes enhancing its performance and personalization via further prompt programming, as well as evaluating the effectiveness of GPTutor with real users.

引用

页码：321 / 327

页数：7

共 7 条

[1]

Brown TB, 2020, ADV NEUR IN, V33

[2] A Decision Model for Designing NLP Applications [J].

Chen, Eason ;

Tseng, Yuen-Hsien .

COMPANION PROCEEDINGS OF THE WEB CONFERENCE 2022, WWW 2022 COMPANION, 2022, :1206-1210

[3]

Grossman K.W., 2012, Tech JobHunt Handbook: Career Management forTechnical Professionals, P193

[4]

Holtzman A, 2020, Arxiv, DOI [arXiv:1904.09751, DOI 10.48550/ARXIV.1904.09751]

[5] Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm [J].

Reynolds, Laria ;

McDonell, Kyle .

EXTENDED ABSTRACTS OF THE 2021 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS (CHI'21), 2021,

[6] Reflections on Educational Choices Made by Coding Bootcamp and Computer Science Graduates [J].

Seibel, Sherry ;

Veilleux, Nanette ;

Miles, Tabitha ;

Beaulieu, Rachel .

PROCEEDINGS OF THE 53RD ACM TECHNICAL SYMPOSIUM ON COMPUTER SCIENCE EDUCATION (SIGCSE 2022), VOL 2, 2022, :1094-1094

[7]

UCAS, 2021, Undergraduate Statistics & Reports

← 1 →