PyTutor：基於ChatGPT之智慧助教提升程式新手學習成效;PyTutor: ChatGPT enabled intelligent tutor to improve the learning Performance of novice programming learners

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Computer Science and Information Engineering > Electronic Thesis & Dissertation > Item 987654321/93009

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/93009

Title:	PyTutor：基於ChatGPT之智慧助教提升程式新手學習成效;PyTutor: ChatGPT enabled intelligent tutor to improve the learning Performance of novice programming learners
Authors:	林季陽;Lin, Ji-Yang
Contributors:	資訊工程學系
Keywords:	智慧助教系統;新手程式教學;ChatGPT;程式解題提示;學習成效;Intelligent Tutor System;Novice Programming;ChatGPT;Program Prompts;Program Hints;Learning Performance
Date:	2023-07-05
Issue Date:	2024-09-19 16:38:22 (UTC+8)
Publisher:	國立中央大學
Abstract:	本研究提出了一種名為PyTutor的智慧助教系統工具，旨在幫助新手學生克服Python程式設計的學習困難。PyTutor提供24小時不間斷的程式引導助教服務，利用ChatGPT模型生成解題提示和程式碼解釋。PyTutor工具針對每題題目提供了五層提示，包括解題方向提示、虛擬碼提示、克漏字程式碼提示、基本程式碼和進階程式碼。此外，PyTutor記錄使用者的相關資訊並提供每週的使用報告。PyTutor工具設計以Chrome Extension為基礎，提供穩定的使用平台，並透過RESTful API的架構形式將邏輯操作傳遞到後端平台。研究結果表明，PyTutor對於程式新手中程式知識較薄弱、測試焦慮情緒高和批判性思考能力低的學生特別有益。此外，使用PyTutor的知識前測低群學生在課堂和課後練習中表現出更高的參與度、完成度和提交正確率。然而，過度依賴PyTutor可能導致學生失去解題思考能力，因此在使用時需要注意適度性。綜上所述，本研究證明了PyTutor作為一個智慧助教系統在程式設計教育中的價值，且能夠針對特定學生族群提升學習成效。;This study proposes a smart assistant system called PyTutor to help novice students overcome the learning difficulties in Python programming. PyTutor provides a 24/7 programming guidance assistant service using the ChatGPT model to generate problem-solving hints and code explanations. The PyTutor tool offers five levels of hints for each problem, including problem-solving direction hints, pseudocode hints, cloze code hints, basic code, and advanced code. Additionally, PyTutor records user information and provides weekly usage reports. The PyTutor tool is designed as a Chrome Extension, providing a stable user platform, and communicates with the backend through a RESTful API architecture. The results of the study demonstrate that PyTutor is particularly beneficial for students who are novices in programming, have weak programming knowledge, experience high test anxiety, and have low critical thinking skills. Furthermore, the knowledge-pretest low group students who used PyTutor showed higher engagement, completion rates, and submission accuracy in both classroom and post-class exercises. However, excessive reliance on PyTutor may lead to a loss of problem-solving thinking skills, so moderation is advised when using the tool. In conclusion, this study confirms the value of PyTutor as a smart assistant system in programming education, specifically in enhancing learning outcomes for targeted student populations.
Appears in Collections:	[資訊工程研究所] 博碩士論文

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	16	View/Open

社群 sharing

Loading...