學術產出-Theses
Article View/Open
Publication Export
-
題名 開發與評估教育聊天機器人：以與課程相關的內容即時支援非資訊領域大學生解決程式設計問題
Development and Evaluation of an Educational Chatbot: Providing Real-Time and Contextual Support for Non-IT University Students Facing Programming Problems作者 林昱辰
Lin, Yu-Chen貢獻者 江玥慧
Chiang, Yueh-Hui
林昱辰
Lin, Yu-Chen關鍵詞 聊天機器人
GPT-4
詞嵌入
餘弦相似性
ChatBot
GPT-4
Word Embedding
Cosine Similarity日期 2023 上傳時間 1-Sep-2023 15:25:48 (UTC+8) 摘要 隨著科技發展，國高中課綱將資訊科技納入必修課程中，希望培養學生的邏輯能力和運算思維。然而，由於課綱修改前後的學生存在學識斷層，進入大學後程式設計程度參差不齊，使得教師在設計個人化教學內容和學習資源方面面臨挑戰；學生們常因害羞或擔心同儕評價而不敢向老師或助教提問。教育聊天機器人的開發可以為學生提供個人化的學習支援，減輕教師和助教的工作負擔，提供學生便利的學習資源的同時給予了較低壓力的環境，讓他們更自在地提問和尋找解答。本研究開發的聊天機器人適用的教學場域為講授基礎Python程式設計觀念的資訊通識課程。研究中使用詞嵌入技術透過餘弦相似度選出與使用者的訊息相近的課程投影片內容來輔助聊天機器人，讓使用者與聊天機器人的對話能夠聚焦於課程討論。
With the development of technology, information technology has been included in the curriculum of junior and senior high schools, aiming to cultivate students` logical reasoning and computational thinking skills. However, due to the disparity in students` knowledge before and after the curriculum revision, there is a significant variation in their programming abilities when they enter university. This poses a challenge for teachers in designing personalized teaching content and learning resources. Additionally, students often hesitate to ask questions of their teachers or teaching assistants due to shyness or concerns about peer evaluation.The development of an educational chatbot can provide personalized learning support to students, alleviate the workload of teachers and teaching assistants, and offer students convenient learning resources in a low-pressure environment. This enables them to feel more comfortable asking questions and seeking answers. The chatbot developed in this research is designed for the educational field of teaching fundamental Python programming concepts in an introductory information technology course. In the research, word embedding techniques are used, and cosine similarity is employed to select course slide content that closely matches the user`s input. This assists the chatbot in focusing on course discussions during interactions with users.參考文獻 [1] 徐文鈺，〈影響大學生課堂主動發言的因素〉，當代教育研究季刊，第 21 卷，第 4 期，頁 41-80，2013 年 12 月。[2] Almeida, F. and Xexéo G., “Word Embeddings: A Survey,” Master`s thesis, Federal University of Rio de Janeiro, Computer and Systems Engineering Program, 2019.[3] Atwood J., and Spolsky J., “Stack Overflow,” Internet: https://stackoverflow.com /, accessed July 23, 2023.[4] Baroni, M., Dinu, G., and Kruszewski, G., “Don’t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors,” Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, Baltimore, Maryland, 2014. doi:10.3115/v1/p14-1023.[5] Brown, T. B. et al., “Language models are few-shot learners,” Advances in Neural Information Processing Systems, Vancouver, Canada, 2020, pp. 1877-1901.[6] Church, K. and Hanks, P., “Word Association Norms, Mutual Information, and Lexicography,” Proceedings of lhe 27th Annual Meeting of the Association for Computational Linguistics, Vancouver, Canada, 1990, pp. 76-83.[7] Cho, K. et al., “Learning phrase representations using RNN encoder–decoder for statistical machine translation,” Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, 2014, pp. 1724-1734. doi:10.3115/v1/d14-1179.[8] Colby, K., Artificial Paranoia: A Computer Simulation of Paranoid Process, New York: Pergamon Press, 1975.[9] Devlin, J., Chang, M.-W., Lee, K. and Toutanova, K., “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding”, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, Minnesota, 2019, pp. 4171-4186. doi: 10.18653/V1/N19-1423.[10] Fielding, R., “Architectural Styles and the Design of Network-based Software Architectures,” Doctoral Dissertation, University of California, Irvine, 2000.[11] fxsjy, “Jieba,” Internet: https://github.com/fxsjy/jieba, accessed July 24, 2023.[12] Goel, A. K., and Polepeddi, L., “Jill Watson: A Virtual Teaching Assistant for Online Education,” Learning Engineering for Online Education, 1st. New York:Routledge, 2016. doi: 10.4324/9781351186193-7.[13] Goldberg, Y. and Graeme, H., “Neural Network Methods for Natural Language Processing,” Toronto, Ontario: Morgan & Claypool Publishers, ISBN: 978-3-031-02165-7, 2017.[14] Hsu, H.-H., and Huang, N.-F., “Xiao-Shih: A self-enriched question answering bot with machine learning on Chinese-based moocs,” IEEE Transactions on Learning Technologies, vol. 15, no. 2, pp. 223-237, Mar. 2022. doi:10.1109/tlt.2022.3162572.[15] Hussain, S., Sianaki, O. A., and Ababneh, N., “A survey on conversational agents/Chatbots classification and Design Techniques,” Advances in Intelligent Systems and Computing, vol. 927. Switzerland:Springer, 2019, pp. 946-956. doi:10.1007/978-3-030-15035-8_93.[16] Jones, K., “Astatistical interpretation of term specificity and its application in retrieval,” Journal of Documentation, Vol. 28 No. 1, pp. 11-21, 1972.[17] Li, F.-F., Fergus, R. and Perona, P., “One-shot learning of object categories,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 4, Piscataway:IEEE Computer Society, Apr. 2006. doi: 10.1109/TPAMI.2006.79.[18] LINE, “LINE Developers” Internet: https://developers.line.biz/ , accessed May 9, 2023.[19] Manning, C., Raghavan, P. and Schütze, H., Introduction to Information Retrieval. Cambridge, U.K.: Cambridge Univ. Press, 2008.[20] Mikolov, T., Chen, K., Corrado, G. S. and Dean, J., “Efficient Estimation of Word Representations in Vector Space,” International Conference on Learning Representations, Scottsdale, Arizona, 2013.[21] Mikolov, T. et al., “Distributed Representations of Words and Phrases and their Compositionality,” Advances in Neural Information Processing Systems, Stateline, America, 2013, pp. 3111-3119.[22] Nss, “An intuitive understanding of word embeddings: From count vectors to word2vec,” Internet: https://www.analyticsvidhya.com/blog/2017/06/word-embeddings-count-word2veec/, accessed May 9, 2023.[23] OpenAI, “Models,” Internet: https://platform.openai.com/docs/models/overview, accessed May 9, 2023.[24] Palatucci, M., Pomerleau, D. A., Hinton, G. E. and Mitchell, T. M., “Zero-shot learning with semantic output codes,” Advances in Neural Information Processing Systems, Vancouver, Canada, 2009, pp. 1410-1418.[25] Radford, A., Sutskever, I., Salimans, T., and Narasimhan, K., “Improving language understanding by generative pre-training,” 2018.[26] Radford, A., Wu, J., Child, R., Luan, D., Amodei, D. and Sutskever, I., “Language models are unsupervised multitask learners,” 2019.[27] Raffel, C. et al, “Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer”, The Journal of Machine Learning Research, vol. 21, no. 140, pp. 5485-5551, May 2020.[28] Robertson, S. and Zaragoza, H., “The probabilistic relevance framework: BM25 and beyond,” Foundations Trends Inf. Retrieval, vol. 3, no. 4, pp. 333–389, Dec. 2009, doi: 10.1561/1500000019.[29] Ulstad, S. O., Halvari, H., Sørebø, Ø., and Deci, E. L., “Motivational predictors of learning strategies, participation, exertion, and performance in Physical Education: A randomized controlled trial,” Motivation and Emotion, vol. 42, no. 4, pp. 497-512, 2018. doi:10.1007/s11031-018-9694-2.[30] Vaswani, A. et al., “Attention is all you need,” Advances in Neural Information Processing Systems, Long Beach, California, 2017, pp. 6000-6010.[31] Wales, J. and Sanger, L., “Wikipedia” Internet: https://www.wikipedia.org/ , accessed May 9, 2023.[32] Wallace, R., “A.L.I.C.E - Artificial Intelligence Foundation,” Internet: http://www.alicebot.org, accessed June 1, 2023.[33] Weizenbaum, J., “ELIZA--A Computer Program For the Study of Natural Language Communication Between Man and Machine,” Communications of the ACM, vol. 9, no. 1, pp. 36–45, 1966. doi:10.1145/365153.365168 描述 碩士
國立政治大學
資訊科學系
110753163資料來源 http://thesis.lib.nccu.edu.tw/record/#G0110753163 資料類型 thesis dc.contributor.advisor 江玥慧 zh_TW dc.contributor.advisor Chiang, Yueh-Hui en_US dc.contributor.author (Authors) 林昱辰 zh_TW dc.contributor.author (Authors) Lin, Yu-Chen en_US dc.creator (作者) 林昱辰 zh_TW dc.creator (作者) Lin, Yu-Chen en_US dc.date (日期) 2023 en_US dc.date.accessioned 1-Sep-2023 15:25:48 (UTC+8) - dc.date.available 1-Sep-2023 15:25:48 (UTC+8) - dc.date.issued (上傳時間) 1-Sep-2023 15:25:48 (UTC+8) - dc.identifier (Other Identifiers) G0110753163 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/147038 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 資訊科學系 zh_TW dc.description (描述) 110753163 zh_TW dc.description.abstract (摘要) 隨著科技發展，國高中課綱將資訊科技納入必修課程中，希望培養學生的邏輯能力和運算思維。然而，由於課綱修改前後的學生存在學識斷層，進入大學後程式設計程度參差不齊，使得教師在設計個人化教學內容和學習資源方面面臨挑戰；學生們常因害羞或擔心同儕評價而不敢向老師或助教提問。教育聊天機器人的開發可以為學生提供個人化的學習支援，減輕教師和助教的工作負擔，提供學生便利的學習資源的同時給予了較低壓力的環境，讓他們更自在地提問和尋找解答。本研究開發的聊天機器人適用的教學場域為講授基礎Python程式設計觀念的資訊通識課程。研究中使用詞嵌入技術透過餘弦相似度選出與使用者的訊息相近的課程投影片內容來輔助聊天機器人，讓使用者與聊天機器人的對話能夠聚焦於課程討論。 zh_TW dc.description.abstract (摘要) With the development of technology, information technology has been included in the curriculum of junior and senior high schools, aiming to cultivate students` logical reasoning and computational thinking skills. However, due to the disparity in students` knowledge before and after the curriculum revision, there is a significant variation in their programming abilities when they enter university. This poses a challenge for teachers in designing personalized teaching content and learning resources. Additionally, students often hesitate to ask questions of their teachers or teaching assistants due to shyness or concerns about peer evaluation.The development of an educational chatbot can provide personalized learning support to students, alleviate the workload of teachers and teaching assistants, and offer students convenient learning resources in a low-pressure environment. This enables them to feel more comfortable asking questions and seeking answers. The chatbot developed in this research is designed for the educational field of teaching fundamental Python programming concepts in an introductory information technology course. In the research, word embedding techniques are used, and cosine similarity is employed to select course slide content that closely matches the user`s input. This assists the chatbot in focusing on course discussions during interactions with users. en_US dc.description.tableofcontents 第1章 緒論 11.1 研究背景 11.2 研究動機與目的 21.3 研究問題 31.4 論文架構 3第2章 文獻探討 42.1 聊天機器人 42.2 Transformer Model 62.3 GPT系列模型 92.4 詞嵌入(Word Embedding) 11第3章 場域說明與系統架構 163.1 場域說明 163.2 系統架構 183.2.1 新增使用者 183.2.2 LINE Bot管理網頁 203.2.3 回覆使用者訊息 223.2.3.1 使用課程投影片輔助聊天機器人 233.2.3.2 LINE Bot如何記錄對話 243.2.4 資料庫 26第4章 系統評估 304.1 評估目的 304.2 評估計劃 304.3 評估結果分析 344.3.1 結果分析(一) ―分析評估者與聊天機器人的對話 354.3.1.1 對話紀錄功能評估 354.3.1.2 課程內容相關問題評估 364.3.1.3 課程範例程式碼解讀 374.3.1.4 程式設計問題解答評估 374.3.1.5 日常對話交流能力評估 374.3.1.6 實作練習相關問題評估 384.3.1.7 期中小組任務相關問題評估 404.3.1.8 網頁設定system功能評估 434.3.1.9 小結―結果分析(一) 434.3.2 結果分析(二) ―分析選出的文本內容 444.3.2.1 對話紀錄功能評估 454.3.2.2 課程內容相關問題評估 464.3.2.3 課程範例程式碼解讀 484.3.2.4 程式設計問題解答評估 494.3.2.5 日常對話交流能力評估 504.3.2.6 實作練習相關問題評估 514.3.2.7 期中小組任務相關問題評估 534.3.2.8 網頁設定system功能評估 564.3.2.9 小結―結果分析(二) 564.3.3 結果分析(三) ―修改Menu功能並評估效果 584.3.3.1 使用評估者的問題測試 584.3.3.2 使用ChatGPT生成的問題測試 604.4 評估結果與討論 62第5章 結論與未來展望 64參考文獻 66附錄A 70附錄B 73附錄C 87 zh_TW dc.format.extent 3800102 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0110753163 en_US dc.subject (關鍵詞) 聊天機器人 zh_TW dc.subject (關鍵詞) GPT-4 zh_TW dc.subject (關鍵詞) 詞嵌入 zh_TW dc.subject (關鍵詞) 餘弦相似性 zh_TW dc.subject (關鍵詞) ChatBot en_US dc.subject (關鍵詞) GPT-4 en_US dc.subject (關鍵詞) Word Embedding en_US dc.subject (關鍵詞) Cosine Similarity en_US dc.title (題名) 開發與評估教育聊天機器人：以與課程相關的內容即時支援非資訊領域大學生解決程式設計問題 zh_TW dc.title (題名) Development and Evaluation of an Educational Chatbot: Providing Real-Time and Contextual Support for Non-IT University Students Facing Programming Problems en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) [1] 徐文鈺，〈影響大學生課堂主動發言的因素〉，當代教育研究季刊，第 21 卷，第 4 期，頁 41-80，2013 年 12 月。[2] Almeida, F. and Xexéo G., “Word Embeddings: A Survey,” Master`s thesis, Federal University of Rio de Janeiro, Computer and Systems Engineering Program, 2019.[3] Atwood J., and Spolsky J., “Stack Overflow,” Internet: https://stackoverflow.com /, accessed July 23, 2023.[4] Baroni, M., Dinu, G., and Kruszewski, G., “Don’t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors,” Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, Baltimore, Maryland, 2014. doi:10.3115/v1/p14-1023.[5] Brown, T. B. et al., “Language models are few-shot learners,” Advances in Neural Information Processing Systems, Vancouver, Canada, 2020, pp. 1877-1901.[6] Church, K. and Hanks, P., “Word Association Norms, Mutual Information, and Lexicography,” Proceedings of lhe 27th Annual Meeting of the Association for Computational Linguistics, Vancouver, Canada, 1990, pp. 76-83.[7] Cho, K. et al., “Learning phrase representations using RNN encoder–decoder for statistical machine translation,” Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, 2014, pp. 1724-1734. doi:10.3115/v1/d14-1179.[8] Colby, K., Artificial Paranoia: A Computer Simulation of Paranoid Process, New York: Pergamon Press, 1975.[9] Devlin, J., Chang, M.-W., Lee, K. and Toutanova, K., “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding”, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, Minnesota, 2019, pp. 4171-4186. doi: 10.18653/V1/N19-1423.[10] Fielding, R., “Architectural Styles and the Design of Network-based Software Architectures,” Doctoral Dissertation, University of California, Irvine, 2000.[11] fxsjy, “Jieba,” Internet: https://github.com/fxsjy/jieba, accessed July 24, 2023.[12] Goel, A. K., and Polepeddi, L., “Jill Watson: A Virtual Teaching Assistant for Online Education,” Learning Engineering for Online Education, 1st. New York:Routledge, 2016. doi: 10.4324/9781351186193-7.[13] Goldberg, Y. and Graeme, H., “Neural Network Methods for Natural Language Processing,” Toronto, Ontario: Morgan & Claypool Publishers, ISBN: 978-3-031-02165-7, 2017.[14] Hsu, H.-H., and Huang, N.-F., “Xiao-Shih: A self-enriched question answering bot with machine learning on Chinese-based moocs,” IEEE Transactions on Learning Technologies, vol. 15, no. 2, pp. 223-237, Mar. 2022. doi:10.1109/tlt.2022.3162572.[15] Hussain, S., Sianaki, O. A., and Ababneh, N., “A survey on conversational agents/Chatbots classification and Design Techniques,” Advances in Intelligent Systems and Computing, vol. 927. Switzerland:Springer, 2019, pp. 946-956. doi:10.1007/978-3-030-15035-8_93.[16] Jones, K., “Astatistical interpretation of term specificity and its application in retrieval,” Journal of Documentation, Vol. 28 No. 1, pp. 11-21, 1972.[17] Li, F.-F., Fergus, R. and Perona, P., “One-shot learning of object categories,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 4, Piscataway:IEEE Computer Society, Apr. 2006. doi: 10.1109/TPAMI.2006.79.[18] LINE, “LINE Developers” Internet: https://developers.line.biz/ , accessed May 9, 2023.[19] Manning, C., Raghavan, P. and Schütze, H., Introduction to Information Retrieval. Cambridge, U.K.: Cambridge Univ. Press, 2008.[20] Mikolov, T., Chen, K., Corrado, G. S. and Dean, J., “Efficient Estimation of Word Representations in Vector Space,” International Conference on Learning Representations, Scottsdale, Arizona, 2013.[21] Mikolov, T. et al., “Distributed Representations of Words and Phrases and their Compositionality,” Advances in Neural Information Processing Systems, Stateline, America, 2013, pp. 3111-3119.[22] Nss, “An intuitive understanding of word embeddings: From count vectors to word2vec,” Internet: https://www.analyticsvidhya.com/blog/2017/06/word-embeddings-count-word2veec/, accessed May 9, 2023.[23] OpenAI, “Models,” Internet: https://platform.openai.com/docs/models/overview, accessed May 9, 2023.[24] Palatucci, M., Pomerleau, D. A., Hinton, G. E. and Mitchell, T. M., “Zero-shot learning with semantic output codes,” Advances in Neural Information Processing Systems, Vancouver, Canada, 2009, pp. 1410-1418.[25] Radford, A., Sutskever, I., Salimans, T., and Narasimhan, K., “Improving language understanding by generative pre-training,” 2018.[26] Radford, A., Wu, J., Child, R., Luan, D., Amodei, D. and Sutskever, I., “Language models are unsupervised multitask learners,” 2019.[27] Raffel, C. et al, “Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer”, The Journal of Machine Learning Research, vol. 21, no. 140, pp. 5485-5551, May 2020.[28] Robertson, S. and Zaragoza, H., “The probabilistic relevance framework: BM25 and beyond,” Foundations Trends Inf. Retrieval, vol. 3, no. 4, pp. 333–389, Dec. 2009, doi: 10.1561/1500000019.[29] Ulstad, S. O., Halvari, H., Sørebø, Ø., and Deci, E. L., “Motivational predictors of learning strategies, participation, exertion, and performance in Physical Education: A randomized controlled trial,” Motivation and Emotion, vol. 42, no. 4, pp. 497-512, 2018. doi:10.1007/s11031-018-9694-2.[30] Vaswani, A. et al., “Attention is all you need,” Advances in Neural Information Processing Systems, Long Beach, California, 2017, pp. 6000-6010.[31] Wales, J. and Sanger, L., “Wikipedia” Internet: https://www.wikipedia.org/ , accessed May 9, 2023.[32] Wallace, R., “A.L.I.C.E - Artificial Intelligence Foundation,” Internet: http://www.alicebot.org, accessed June 1, 2023.[33] Weizenbaum, J., “ELIZA--A Computer Program For the Study of Natural Language Communication Between Man and Machine,” Communications of the ACM, vol. 9, no. 1, pp. 36–45, 1966. doi:10.1145/365153.365168 zh_TW
