PyChatBot：結合ChatGPT與LineBot的ChatBot用於提升學生總結寫作能力;PyChatBot: ChatBot combining ChatGPT and LineBot is used to improve students′ summary writing ability

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Computer Science and Information Engineering > Electronic Thesis & Dissertation > Item 987654321/93005

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/93005

Title:	PyChatBot：結合ChatGPT與LineBot的ChatBot用於提升學生總結寫作能力;PyChatBot: ChatBot combining ChatGPT and LineBot is used to improve students′ summary writing ability
Authors:	顏若軒;Yen, Ruo-Xuan
Contributors:	資訊工程學系
Keywords:	聊天機器人;總結寫作反饋;學習分析;LIME;ChatBot in Education;Summary Writing Feedback;Learning Analytics;LIME
Date:	2023-07-05
Issue Date:	2024-09-19 16:38:15 (UTC+8)
Publisher:	國立中央大學
Abstract:	本研究探討了使用聊天機器人以提升學生總結寫作能力，並分析學生的學習行為與學習成效間的關聯性。聊天機器人可以提供學習者即時的幫助，節省等待助教或教師回復的時間，從而提高學習效率。此外，聊天機器人也可以通過一對一的交談方式提供個性化學習。然而，在教育領域中，大部分對聊天機器人的評估都是使用學生問卷，很少有對學生的學習行為進行分析。在本研究中，我們開發了一個名為PyChatBot的聊天機器人，作為學生的課後輔助學習工具。除了提供總結寫作反饋外，它還作為學生和助教之間的交流平台。在學生提問時，PyChatBot會自動抓取學生在線上解題環境中的作答紀錄，並發送給助教，以幫助助教更好地理解學生的問題。本研究旨在通過使用PyChatBot收集學生的學習歷程，並進行總結寫作反饋活動，探討基於LIME的總結寫作反饋對學生總結寫作能力的影響，以及總結寫作分數與程式概念和程式實作學習成效的相關性。此外，我們還將探討在使用聊天機器人時，哪些學習行為與學習成效有關。在總結寫作反饋的生成方面，我們使用了ChatGPT來輔助教師生成反饋所需的相關教材，並使用SBERT代替傳統的LSA，以減輕教師的負擔。實驗結果表明，使用結合ChatGPT與LineBot的聊天機器人能有效地提升學生總結寫作能力，且評估出的總結寫作分數與學生的程式概念分數存在顯著的相關性，在學習分析的方面，我們發現學生的學習成效與使用聊天機器人各個功能的次數無關，只與使用的時間有所相關。 ;This study aims to investigate the effectiveness of utilizing chatbots to enhance students′ summary writing skills and to analyze the relationship between students′ learning behavior and their learning outcome. Chatbots offer immediate support to learners, reducing the wait time for assistance and improving overall learning efficiency. Moreover, chatbots provide personalized learning experiences through one-on-one interactions. In this research, we developed PyChatBot as a tool for students′ post-class learning assistance. Alongside providing feedback on summary writing, PyChatBot serves as a platform for communication between students and teaching assistants. The study focuses on utilizing PyChatBot to gather students′ learning processes and conduct summary writing feedback activities. It explores the impact of LIME-based summary writing feedback on students′ summarization abilities, as well as the correlation between summary writing scores and learning outcomes. Additionally, the study aims to identify the learning behaviors that relate to learning outcomes when using chatbots. To generate summary writing feedback, we employed ChatGPT to assist teachers in producing relevant instructional materials and substituted traditional LSA with SBERT to alleviate the workload for teachers. Experimental results indicate that incorporating a chatbot that combines ChatGPT and LineBot effectively enhances students′ summary writing skills. There is a significant correlation between summary writing scores and students′ programming concept scores . Regarding learning analytics, the study found that students′ learning outcomes are unrelated to the frequency of using specific chatbot functions but rather depend on the duration of usage.
Appears in Collections:	[Graduate Institute of Computer Science and Information Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	14	View/Open

社群 sharing

Loading...