臺灣博碩士論文加值系統

學習程式設計成為必要且重要的存在，但學習者從零建立基礎到實作應用並不容易。生成式AI的出現提供了工具給學習者輔助，然而由於使用上的高度依賴以及生成結果的不正確性，仍會在學習成效以及未來對工具的使用上造成負面影響。以運算思維運用之，透過對問題的拆解，使用者各別對輸入、輸出、處理方式等各細節分別描述，提高生成式AI對問題的理解。本研究提出從案例式學習防止學習者高度依賴生成式AI以及避免其生成結果的不正確性，以過往案例的解題經驗來延伸應用學習者既有的程式觀念，幫助學習者以運算思維的方式使用生成式AI，利用精準的自然語言建構解題方法，提升學習者學習程式設計時的成效。本研究以此方式設計了一套學習系統，並實施為期十三週的實驗，實驗結果顯示，有別於學習者在電腦環境下直接實作並將完整問題給予生成式AI進行問答的學習方法，以本研究所設計的學習系統學習程式設計，在成效上有著更顯著的效果。

Learning programming has become a necessary and important skill, but it is not easy for learners to build a foundation from scratch and apply it in practice. The emergence of generative AI provides a tool to assist learners, but due to high dependency and the inaccuracy of generated results, it can negatively impact learning effectiveness and future use of the tool. By applying computational thinking, users can improve the understanding of generative AI by describing each detail of inputs, outputs, and processing methods through problem decomposition. This study proposes case-based learning to prevent learners from becoming highly dependent on generative AI and to avoid inaccuracies in generated results. By extending the application of learners' existing programming concepts through problem-solving experiences from past cases, this approach helps learners use generative AI with computational thinking, constructing problem-solving methods with precise natural language to improve their effectiveness in learning programming. This study designed a learning system based on this approach and conducted a thirteen-week experiment. The results showed that, compared to learners directly implementing and querying generative AI in a computer environment, learning programming using the system designed in this study had more significant effects on learning outcomes.

一、 緒論 1
1.1 研究背景與動機 1
1.2 研究問題以及解決辦法 5
二、 文獻探討 9
2.1 運算思維 9
2.2 案例式學習 10
2.3 生成式 AI 與提示方法 11
三、 學習方法與實作 13
3.1 方法概述 13
3.2 系統介面 15
3.2.1 登入以及題目選擇介面 16
3.2.2 製作模組介面 17
3.2.3 生成結果以及修正介面 20
3.3 學習流程-遞迴的程式主題 23
3.4 系統實作 33
3.4.1 運算思維模組JSON與生成結果JSON 36
3.4.2 資料庫
四、 實驗設計 41
4.1 研究對象 41
4.2 實驗流程 41
4.3 學習內容 42
4.3.1 中測前實驗 43
4.3.2 中測後實驗 46
4.4 程式能力前、中、後測測驗 49
五、 實驗結果以及討論 53
5.1 描述統計分析結果 53
5.2 學習成效分析工具 54
5.2.1 常態分佈檢定 54
5.2.2 變異數同質性檢定 55
5.2.3 Mauchly’s 球形檢定 56
5.2.4 單因子相依變異數分析 57
5.2.5 成對比較 58
5.3 受試者回饋 60
5.4 學習成效結果討論 62
5.5 研究限制 63
六、 結論與未來展望 65
6.1 結論 65
6.2 未來展望 66

Abesadze, S., & Nozadze, D. (2020). Make 21st century education: The importance of teaching programming in schools. International Journal of Learning and Teaching, 6(3), 6.

Affleck, G., & Smith, T. (1999). Identifying a need for web-based course support. ASCILITE, 99.

Allen, J. M., Vahid, F., Edgcomb, A., Downey, K., & Miller, K. (2019). An analysis of using many small programs in cs1. Proceedings of the 50th ACM Technical Symposium on Computer Science Education, 585–591. https://doi.org/10.1145/3287324.3287466

Amershi, S., Weld, D., Vorvoreanu, M., Fourney, A., Nushi, B., Collisson, P., Suh, J., Iqbal, S., Bennett, P. N., Inkpen, K., et al. (2019). Guidelines for human-ai interaction. Proceedings of the 2019 chi conference on human factors in computing systems, 1–13.

Ashley, K. D. (1992). Case-based reasoning and its implications for legal expert systems. Artificial Intelligence and Law, 1(2), 113–208.

Ayman, S. E., El-Seoud, S. A., Nagaty, K., & Karam, O. H. (2023). The influence of chatgpt on student learning and academic performance. 2023 International Conference on Computer and Applications (ICCA), 1–5. https://doi.org/10.1109/ICCA59364.2023.10401713

Baldassarre, M. T., Caivano, D., Fernandez Nieto, B., Gigante, D., & Ragone, A. (2023). The social impact of generative ai: An analysis on chatgpt. Proceedings of the 2023 ACM Conference on Information Technology for Social Good, 363–373.

Barke, S., James, M. B., & Polikarpova, N. (2023). Grounded copilot: How programmers interact with code-generating models. Proc. ACM Program. Lang., 7(OOPSLA1). https://doi.org/10.1145/3586030

Becker, B. A., Craig, M., Denny, P., Keuning, H., Kiesler, N., Leinonen, J., Luxton-Reilly, A., Prather, J., & Quille, K. (2023). Generative ai in introductory programming.

Bennedsen, J., & Caspersen, M. E. (2007). Failure rates in introductory programming. SIGCSE Bull., 39(2), 32–36. https://doi.org/10.1145/1272848.1272879

Bosse, Y., & Gerosa, M. A. (2017). Why is programming so difficult to learn? patterns of difficulties related to programming learning mid-stage. ACM SIGSOFT Software Engineering Notes, 41(6), 1–6.

Brown, N., & Wilson, G. (2018). Ten quick tips for teaching programming. PLOS Computational Biology, 14, e1006023. https://doi.org/10.1371/journal.pcbi.1006023

Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020). Language models are few-shot learners. Advances in neural information processing systems, 33, 1877–1901.

Budak, E. Ç., Geçer, A. K., & Topal, A. D. (2021). The effect of programming with scratch course on reflective thinking skills of students towards problem solving. Journal of Learning and Teaching in Digital Age, 6(1), 72–80.

Cabo, C. (2023). Developing and documenting problem-solving strategies for computer programming before code writing. 2023 IEEE Frontiers in Education Conference (FIE), 1–5. https://doi.org/10.1109/FIE58773.2023.10343169

Cheah, C. S. (2020). Factors contributing to the difficulties in teaching and learning of computer programming: A literature review. Contemporary Educational Technology, 12(2), ep272.

Chen, W.-F., & Yeh, K.-C. (2006). Work in progress: Creating a case-based reasoning digital library to improve learning in an introductory programming course. Proceedings. Frontiers in Education. 36th Annual Conference, 21–22.

Chung, I.-L., Chou, C.-M., Hsu, C.-P., & Li, D.-K. (2016). A programming learning diagnostic system using case-based reasoning method. 2016 International Conference on System Science and Engineering (ICSSE), 1–4.

Davies, S. (2008). The effects of emphasizing computational thinking in an introductory programming course. 2008 38th Annual Frontiers in Education Conference, T2C-3-T2C–8. https://doi.org/10.1109/FIE.2008.4720362

Denny, P., Leinonen, J., Prather, J., Luxton-Reilly, A., Amarouche, T., Becker, B. A., & Reeves, B. N. (2024). Prompt problems: A new programming exercise for the generative ai era. Proceedings of the 55th ACM Technical Symposium on Computer Science Education V. 1, 296–302. https://doi.org/10.1145/3626252.3630909

Deriba, F. G., Sanusi, I. T., & Sunday, A. O. (2023). Enhancing computer programming education using chatgpt-a mini review. Proceedings of the 23rd Koli Calling International Conference on Computing Education Research, 1–2.

Elisabet, D., Sensuse, D. I., & Al Hakim, S. (2019). Implementation of case-method cycle for case-based reasoning in human medical health: A systematic review. 2019 3rd International Conference on Informatics and Computational Sciences (ICICoS), 1–6. https://doi.org/10.1109/ICICoS48119.2019.8982438

Fuchs, K. (2023). Exploring the opportunities and challenges of nlp models in higher education: Is chat gpt a blessing or a curse? Frontiers in Education, 8, 1166682.

Geng, C., Zhang, Y., Pientka, B., & Si, X. (2023). Can chatgpt pass an introductory level functional language programming course?

Gick, M. L. (1986). Problem-solving strategies. Educational psychologist, 21(1-2), 99–120.

Guo, Y., & Lee, D. (2023). Leveraging chatgpt for enhancing critical thinking skills. Journal of Chemical Education, 100(12), 4876–4883.

Handayani, R. D., Lesmono, A. D., Prastowo, S. B., Supriadi, B., & Dewi, N. M. (2022). Bringing computational thinking skills into physics classroom through project-based learning. 2022 8th International Conference on Education and Technology (ICET), 76–80. https://doi.org/10.1109/ICET56879.2022.9990631

Jonassen, D. H., & Hernandez-Serrano, J. (2002). Case-based reasoning and instructional design: Using stories to support problem solving. Educational technology research and development, 50(2), 65–77.

Kalla, D., & Smith, N. (2023). Study and analysis of chat gpt and its impact on different fields of study. International Journal of Innovative Science and Research Technology, 8(3), 827–833.

Kolodner, J. (2014). Case-based reasoning. Morgan Kaufmann.

Lahtinen, E., Ala-Mutka, K., & Järvinen, H.-M. (2005). A study of the difficulties of novice programmers. Proceedings of the 10th Annual SIGCSE Conference on Innovation and Technology in Computer Science Education, 14–18. https://doi.org/10.1145/1067445.1067453

Madotto, A., Lin, Z., Winata, G. I., & Fung, P. (2021). Few-shot bot: Prompt-based learning for dialogue systems.

Nist. dictionary of algorithms and data structures. (n.d.). Retrieved May 15, 2024, from https://xlinux.nist.gov/dads/

Polya, G. (1945). How to solve it? Princeton University Press.

Portnoff, S. R. (2018). The introductory computer programming course is first and foremost a language course. ACM Inroads, 9(2), 34–52.

Qadir, J. (2023). Engineering education in the era of chatgpt: Promise and pitfalls of generative ai for education. 2023 IEEE Global Engineering Education Conference (EDUCON), 1–9.

Qureshi, B. (2023). Exploring the use of chatgpt as a tool for learning and assessment in undergraduate computer science curriculum: Opportunities and challenges. arXiv preprint arXiv:2304.11214.

Rahman, M. M., & Watanobe, Y. (2023). Chatgpt for education and research: Opportunities, threats, and strategies. Applied Sciences, 13(9), 5783.

Rasul, T., Nair, S., Kalendra, D., Robin, M., de Oliveira Santini, F., Ladeira, W. J., Sun, M., Day, I., Rather, R. A., & Heathcote, L. (2023). The role of chatgpt in higher education: Benefits, challenges, and future research directions. Journal of Applied Learning and Teaching, 6(1).

Ratcliff, B., & Siddiqi, J. I. (1985). An empirical investigation into problem decomposition strategies used in program design. International Journal of Man-Machine Studies, 22(1), 77–90.

Reinfelds, J. (1995). A three paradigm first course for cs majors. ACM SIGCSE Bulletin, 27(1), 223–227.

Sanh, V., Webson, A., Raffel, C., Bach, S. H., Sutawika, L., Alyafeai, Z., Chaffin, A., Stiegler, A., Scao, T. L., Raja, A., et al. (2021). Multitask prompted training enables zero-shot task generalization. arXiv preprint arXiv:2110.08207.

Selby, C. C. (2012). Promoting computational thinking with programming. Proceedings of the 7th workshop in primary and secondary computing education, 74–77.

Shute, V. J. (2008). Focus on formative feedback. Review of educational research, 78(1), 153–189.

Stahl, M., Biermann, L., Nehring, A., & Wachsmuth, H. (2024). Exploring llm prompting strategies for joint essay scoring and feedback generation.

Travers, M. D. (1996). Programming with agents new metaphors for thinking about computation [Doctoral dissertation, Massachusetts Institute of Technology].

Vaithilingam, P., Zhang, T., & Glassman, E. L. (2022). Expectation vs. experience: Evaluating the usability of code generation tools powered by large language models. Extended Abstracts of the 2022 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3491101.3519665

Voskoglou, M. G., & Buckley, S. (2012). Problem solving and computational thinking in a learning environment. arXiv preprint arXiv:1212.0750.

Watson, I. (1999). Case-based reasoning is a methodology not a technology. Knowledge-Based Systems, 12(5), 303–308. https://doi.org/https://doi.org/10.1016/S0950-7051(99)00020-9

Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., Le, Q. V., Zhou, D., et al. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35, 24824–24837.

Welcome to flask —flask documentation (3.0.x). (n.d.). Retrieved May 15, 2024, from https://flask.palletsprojects.com/en/3.0.x/

Wing, J. M. (2006). Computational thinking. Communications of the ACM, 49(3), 33–35.

Wolz, U., Stone, M., Pulimood, S. M., & Pearson, K. (2010). Computational thinking via interactive journalism in middle school. Proceedings of the 41st ACM Technical Symposium on Computer Science Education, 239–243. https://doi.org/10.1145/1734263.1734345

Yadav, A., Zhou, N., Mayfield, C., Hambrusch, S., & Korb, J. T. (2011). Introducing computational thinking in education courses. Proceedings of the 42nd ACM technical symposium on Computer science education, 465–470.

Zhang, Y. (2023). Generative ai has lowered the barriers to computational social sciences. arXiv preprint arXiv:2311.10833.

Zhong, R., Lee, K., Zhang, Z., & Klein, D. (2021). Adapting language models for zero-shot learning by meta-tuning on dataset and prompt collections. arXiv preprint arXiv:2104.04670.

教育部智慧創新跨域人才培育計畫,大學程式設計先修測驗. (n.d.). Retrieved May 15, 2024, from https://apcs.csie.ntnu.edu.tw/