政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/153394

政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/153394

English | 正體中文 | 简体中文 | Post-Print筆數 : 27 | Items with full text/Total items : 113318/144297 (79%)
Visitors : 50954677 Online Users : 976

RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.

Scope

please add "double quotation mark" for query phrases to get precise results

please goto advance search for comprehansive author search

Adv. Search

Home ‧ Login ‧ Upload ‧ Help ‧ About ‧ Administer

Goto mobile version

政大典藏 > College of Informatics > Department of Computer Science > Theses > Item 140.119/153394

Please use this identifier to cite or link to this item: https://nccur.lib.nccu.edu.tw/handle/140.119/153394

Title:	探究使用者之合作傾向對其與ChatGPT完成協作任務的影響 Exploring the Impact of Users’ Cooperative Tendencies on the Completion of Collaboration Tasks with ChatGPT
Authors:	楊千萱 Yang, Chien-Hsuan
Contributors:	江玥慧 Chiang, Yueh-Hui 楊千萱 Yang, Chien-Hsuan
Keywords:	ChatGPT 協作問題解決合作傾向概念地圖 ChatGPT Collaborative Problem Solving(CPS) Cooperative Tendency Concept Map
Date:	2024
Issue Date:	2024-09-04 15:02:45 (UTC+8)
Abstract:	ChatGPT的出現讓許多人通過自然語言，就能產生各種形式的內容，以達成目標。但是它並非總能提供符合需求的資訊，為了瞭解使用者的合作能力與其在短時間內讓ChatGPT產生正確結果的能力之間有無關聯，本研究設計與ChatGPT協作任務的實驗，來探討使用者外在的協作能力、內在的合作傾向與最終成果的關聯性。本研究於實驗中要求使用者不斷與ChatGPT討論，最後讓它繪製出一張程式碼概念圖。除此之外，藉由團隊合作量表來評估使用者的合作傾向，並採用CRESST 團隊開發的協作解決問題模型，使用內容分析從使用者與ChatGPT對話中，分析出最常使用的協作能力。最後將合作傾向、協作能力以及程式碼概念圖等資料，使用相關性分析來觀察彼此間的關聯性。研究結果顯示，使用者更偏向使用「協調能力」，不經篩選直接採納ChatGPT的資訊，這也影響到最終的成品缺乏創意性與豐富性。同時也觀察到在合作中較傾向使用「協商」態度的使用者與ChatGPT會互為領導者，當使用者被領導時，會以較開放的方式去接收資訊，換使用者領導時則比較常指派任務或選擇最佳解決方案。另外，使用者分別採用不同的合作態度來處理ChatGPT給予的回饋，無論哪種合作傾向都與繪圖的部分成果呈正相關，這與本研究最初的假設「擅於合作的人，擅於使用ChatGPT」一致。 The emergence of ChatGPT has enabled many people to generate various forms of content to achieve their goals using natural language. However, it doesn't always provide information that meets the requirements. To understand if there's a correlation between users' collaborative abilities and their capacity to produce accurate results with ChatGPT in a short time, this study designed experiments involving collaborative tasks with ChatGPT to explore the relationship between users' external collaborative abilities, internal cooperative tendencies, and final outcomes. In the experiment, users were required to continuously discuss with ChatGPT, ultimately having it draw a program code concept map. Additionally, a teamwork scale was used to assess users' cooperative tendencies, and the CRESST team's collaborative problem-solving model was adopted to analyze the most frequently used collaborative skills in the dialogue between users and ChatGPT through content analysis. Finally, correlation analysis was used to observe the relationships among cooperative tendencies, collaborative abilities, and the program code concept map data. The research results show that users tend to use "coordination skills" more, directly adopting information from ChatGPT without filtering, which affects the final product's lack of creativity and richness. It was also observed that users who tend to use a "negotiation" attitude in collaboration take turns being leaders with ChatGPT. When users are led, they tend to receive information more openly, and when users lead, they more often assign tasks or choose the best solutions. Moreover, users adopt different cooperative attitudes to handle feedback from ChatGPT, and regardless of the type of cooperative tendency, it shows a positive correlation with some aspects of the drawing results. This is consistent with the study's initial hypothesis that "people who are good at cooperation are good at using ChatGPT."
Reference:	[1] A. Azaria, “ChatGPT Usage and Limitations.,” hal-03913837, Israel, 2022. [2] C. V. Boxtel, J. V. D. Linden, E. Roelofs, & G. Erkens, “Collaborative Concept Mapping: Provoking and Supporting Meaningful Discourse,” Theory Into Practice 41(1),, p. 40–46, 2002. [3] D. Djukanovic &. C. Radoje, “Validation of Propensity to Cooperation Questionnaire,” Communication Strategies & Consulting d.o.o, 2022. [4] D. P. Ausubel, Educational psychology: a cognitive view, NewYork: Holt,Rinehart & Winston of Canada Ltd, 1968. [5] F. Hesse, E.Care, J.Buder, K. Sassenberg, & P. Griffin, “ A framework for teachable collaborative problem solving skills,” Assessment and teaching of 21st century skills, pp. 37-56, 2015. [6] H. E. Herl, G. K. W. K. Chung, & H. F. O’Neil, “The use of computer-based collaborative knowledge mapping to measure team processes and team outcomes,” Computers in Human Behavior, pp. 463-493, 1999. [7] H. F. O'Neil, S. H. Chuang, & G. K. W. K. Chung, “Issues in the Computer-Based Assessment of Collaborative Problem Solving,” National Center for Research on Evaluation, Standards, and Student Testing (CRESST), Los Angeles, 2004. [8] J. Roschelle &. S. D. Teasley, “The Construction of Shared Knowledge in Collaborative Problem Solving,” Computer Supported Collaborative Learning, Springer, Berlin, Heidelberg, 1995. [9] J. D. Novak &. D. B. Gowin, Learning how to learn, Cambridge University Press, 1984. [10] K. Cavdar & T. Temizel,“Analyzing the effects of the personality traits on the success of online collaborative groups,” Social and Behavioral Sciences 228, p. 383 – 389, 2016. [11] L. Wang, C. MacCann, X. Zhuang, O. L. Liu, & R. D. Roberts, “Assessing Teamwork and Collaboration in High School Students: A Multimethod Approach,” Canadian Journal of School Psychology, pp. 108-124, 2009. [12] OECD, “PISA 2015 Draft Collaborative Problem Solving Framework.,” OECD, 2013. [13] P. Dillenbourg, M. Baker, A. Blaye, & C. O'Malley, “The evolution of research on collaborative learning.,” Learning in Humans and Machine: Towards an interdisciplinary learning science, pp. 189-211, 1996. [14] P. P. Ray, “ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope,” Internet of Things and Cyber-Physical Systems, pp. 121-154, 2023. [15] P. K. Anita, A. Pasztor, & G.Molnar, “Measuring collaborative problem solving: research agenda and assessment instrument,” Interactive Learning Environments, pp. 1-21, 2021. [16] T. Panitz, “Collaborative versus Cooperative Learning: A Comparison of the Two Concepts Which Will Help Us Understand the Underlying Nature of Interactive Learning,” 1999. [17] T. Walle. &. J. E. Hannay, “Personality and the nature of collaboration in pair programming,” 3rd International Symposium on Empirical Software Engineering and Measurement, pp. 203-213, 2009. [18] 方朝郁, “概念構圖在國小自然與生活科技領域教學上的應用,” 教育研究, pp. 127-138, 2005. [19] 郭佳甄, “初探高一生在弱結構問題之協作問題解決能力和其協作互動歷程,” 臺灣師範大學, 2016.
Description:	碩士國立政治大學資訊科學系 111753227
Source URI:	http://thesis.lib.nccu.edu.tw/record/#G0111753227
Data Type:	thesis
Appears in Collections:	[Department of Computer Science ] Theses

Files in This Item:

File	Description	Size	Format
322701.pdf		2722Kb	Adobe PDF	0	View/Open

All items in 政大典藏 are protected by copyright, with all rights reserved.

社群 sharing

著作權政策宣告 Copyright Announcement

1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.

DSpace Software Copyright © 2002-2004 MIT & Hewlett-Packard / Enhanced by NTU Library IR team Copyright © - Feedback