Since generative AI (GenAI) launched, interactions between humans and artificial intelligence have rapidly evolved. This study explores how discourse practices in human–AI interactions influence collaborative problem-solving with ChatGPT. Grounded in small group dynamics research, the investigation examines whether three discourse practices (i.e., construction, co-construction, and constructive conflict) help users and ChatGPT find common ground (i.e., shared cognition) to effectively and efficiently complete creative writing projects. Participants completed creative writing projects using ChatGPT for a month and subsequently responded to surveys assessing discourse practices, shared cognition, team effectiveness, and concepts from the Technology Acceptance Model (TAM). Results indicate that discourse practices significantly predict shared cognition, which in turn mediates the relationship between discourse practices and perceived team effectiveness. Furthermore, shared cognition positively influences behavioral intentions to use ChatGPT, primarily through its effects on perceived ease of use and perceived usefulness, aligning with TAM predictions. These findings have important implications for understanding users’ communication styles, suggesting that principles from human-to-human interactions can and should be applied to AI conversations. The current study proposes that ChatGPT is capable of mirroring and reciprocating these discourse practices, which may open the possibility to begin optimizing dialogue with GenAI similar to the goals of prompt engineering.
LiuV, ChiltonLB. Design guidelines for prompt engineering text-to-image generative models. Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems; 2022:1–23.
3.
WangM, WangM, XuX, et al.Unleashing ChatGPT’s power: A case study on optimizing information retrieval in flipped classrooms via prompt engineering. IEEE Trans Learning Technol, 2024; 17:629–641; doi: 10.1109/TLT.2023.3324714
4.
KwonK, KimK. Exploring Middle School Teachers’ Experience in Co-design and Co-teach an NLP-Generative AI focused curriculum in STEM classroom. Society for Information Technology & Teacher Education International Conference; 2024: Association for the Advancement of Computing in Education (AACE); 2024; pp. 2520–2522.
5.
Van den BosscheP, GijselaersWH, SegersM, et al.Social and cognitive factors driving teamwork in collaborative learning environments: Team learning beliefs and behaviors. Small Group Research, 2006; 37(5):490–521; doi: 10.1177/1046496406292938
6.
MathieuJE, HeffnerTS, GoodwinGF, et al.The influence of shared mental models on team process and performance. J Appl Psychol, 2000; 85(2):273–283; doi: 10.1037/0021-9010.85.2.273
7.
ResnickLB, LevineJM, TeasleySD. Perspectives on Socially Shared Cognition: American Psychological Association: Washington, DC; 1991.
8.
VelezJA, SchmierbachM, SherrickB, et al.A recipe for success: The effect of dyadic communication and cooperative gameplay on subsequent non-gaming task performance. Human Communication Research, 2021; 47(4):364–386; doi: 10.1093/hcr/hqab008
9.
DavisFD. Perceived usefulness, perceived ease of use, and user acceptance of information technology. Mis Q, 1989; 13(3):319–340; doi: 10.2307/249008
10.
KnothN, TolzinA, JansonA, et al.AI literacy and its implications for prompt engineering strategies. Computers and Education: Artificial Intelligence, 2024; 6:100225; doi: 10.1016/j.caeai.2024.100225
11.
MeskóB. Prompt engineering as an important emerging skill for medical professionals: Tutorial. J Med Internet Res, 2023; 25:e50638; doi: 10.2196/50638
12.
Velásquez-HenaoJD, Franco-CardonaCJ, Cadavid-HiguitaL. Prompt Engineering: A methodology for optimizing interactions with AI-Language Models in the field of engineering. Dyna, 2023; 90(230):9–17; doi: 10.15446/dyna.v90n230.111700
13.
LeungCH. Promoting optimal learning with ChatGPT: A comprehensive exploration of prompt engineering in education. 5052, 2024; 8(2):104–114.
14.
NgoTT, AnGK, NguyenPT, et al.Unlocking educational potential: Exploring students’ satisfaction and sustainable engagement with ChatGPT using the ECM model. Journal of Information Technology Education: Research, 2024; 23:021; doi: 10.28945/5344
15.
OuyangL, WuJ, JiangX, et al.Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 2022; 35:27730–27744.
16.
VinyalsO, LeQ. A neural conversational model. arXiv [Preprint] arXiv:1506.05869. 2015.
17.
WebbNM, FrankeML, DeT, et al.‘Explain to your partner’: teachers’ instructional practices and students’ dialogue in small groups. Cambridge Journal of Education, 2009; 39(1):49–70; doi: 10.1080/03057640802701986
18.
RepiceMD, SawyerRK, HogrebeMC, et al.Talking through the problems: A study of discourse in peer-led small groups. Chem Educ Res Pract, 2016; 17(3):555–568; doi: 10.1039/C5RP00154D
19.
WeinbergerA, StegmannK, FischerF. Knowledge convergence in collaborative learning: Concepts and assessment. Learning and Instruction, 2007; 17(4):416–426; doi: 10.1016/j.learnstruc.2007.03.007
20.
WebbNM. Group processes in the classroom. Handbook of Educational Psychology. (BerlinerD, CalfeeR. eds) MacMillan: New York; 1996; pp. 841–876.
21.
CummingsTG. Co-constructivism in educational theory and practice. International encyclopedia of the social and behavioral sciences. Elsevier: Amsterdam; 2001; 11:2058–62.
22.
BakerM. A model for negotiation in teaching-learning dialogues. Journal of Interactive Learning Research, 1994; 5(2):199–254.
23.
RoschelleJ. Learning by collaborating: Convergent conceptual change. In Cscl, 2012 (pp. 209–248). Routledge.
24.
MaJ, WangP, LiB, et al.Exploring User Adoption of ChatGPT: A Technology Acceptance Model Perspective. International Journal of Human-Computer Interaction, 2025; 41(2):1431–1445; doi: 10.1080/10447318.2024.2314358
25.
KuangYR, ZouMX, NiuHQ, et al.ChatGPT encounters multiple opportunities and challenges in neurosurgery. Int J Surg, 2023; 109(10):2886–2891; doi: 10.1097/JS9.0000000000000571
26.
FaulF, ErdfelderE, BuchnerA, et al.Statistical power analyses using G* Power 3.1: Tests for correlation and regression analyses. Behav Res Methods, 2009; 41(4):1149–1160.
NasirL, NaqviSM, BhamaniS. Enhancing Students’ Creative Writing Skills: An Action Research Project. Acta Didactica Napocensia, 2013; 6(2):27–32.
29.
HayesAF. PROCESS Macro for SPSS (Version 4.2). 2014. http://www.processmacro.org [Last accessed: October, 2024].
30.
HayesAF. Mediation, moderation, and conditional process analysis. In: Introduction to Mediation, Moderation, and Conditional Process Analysis: A Regression-Based Approach. Guilford Press: New York; 2013; 1(6):12–20.
31.
Cong-LemN, SoyoofA, TseringD. A systematic review of the limitations and associated opportunities of ChatGPT. International Journal of Human-Computer Interaction, 2024:1–16; doi: 10.1080/10447318.2024.2344142
32.
SamadiMA, JaQuayS, GuJ, et al.The AI Collaborator: Bridging Human-AI Interaction in Educational and Professional Settings. arXiv Preprint, 2024; doi: 10.48550/arXiv.2405.10460arXiv:2405.10460
YuanB, HuJ. Generative AI as a Tool for Enhancing Reflective Learning in Students. arXiv, 2024; doi: 10.48550/arXiv.2412.02603 (Cornell University)
35.
SadeghianS, HassenzahlM. The” artificial” colleague: Evaluation of work satisfaction in collaboration with non-human coworkers. In Proceedings of the 27th International Conference on Intelligent User Interfaces 2022 (pp. 27–35); doi: 10.1145/3490099.3511128
