English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 80990/80990 (100%)
造訪人次 : 42654391      線上人數 : 1153
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋


    請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/93009


    題名: 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
    作者: 林季陽;Lin, Ji-Yang
    貢獻者: 資訊工程學系
    關鍵詞: 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
    日期: 2023-07-05
    上傳時間: 2024-09-19 16:38:22 (UTC+8)
    出版者: 國立中央大學
    摘要: 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.
    顯示於類別:[資訊工程研究所] 博碩士論文

    文件中的檔案:

    檔案 描述 大小格式瀏覽次數
    index.html0KbHTML16檢視/開啟


    在NCUIR中所有的資料項目都受到原著作權保護.

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 隱私權政策聲明