Effectiveness of User Interaction with ChatGPT: Sociolinguistic Aspects of Politeness
DOI:
https://doi.org/10.31649/1997-9266-2026-186-3-153-159Keywords:
artificial intelligence, ChatGPT, LLM, NLP, user, prompt, linguistic etiquette, politenessAbstract
Research of the impact of politeness on user interaction with artificial intelligence (AI) is a topical area of contemporary interdisciplinary studies. This article examines the sociolinguistic aspects of politeness as a factor in communication culture from the perspective of its impact on the effectiveness of working with AI, and outlines the significance of linguistic etiquette for digital communication with large AI-based language models. The relevance of the study, on the one hand, is connected with the rapid increase of user queries to artificial intelligence, which is gradually influencing the formation of new models of digital communication and the nature of the system’s responses. On the other hand, it is important to investigate the influence of politeness on user interaction with AI through the Ukrainian language, which broadens the scientific understanding of politeness in human-machine interaction.
To investigate the impact of politeness in prompts on the effectiveness of user-AI interaction, a survey method was used as the primary approach. The method was implemented using Google Forms, a survey administration software from Google. The survey, conducted between 2025 and 2026, involved 176 first- and second-year students of both genders from seven faculties at Vinnitsa National Technical University. Descriptive, comparative and statistical methods were used to interpret the results and analyze the empirical data from the survey. A comparative analysis of the text results generated by artificial intelligence was carried out by several indicators: using phrases of neutral, highly emotive and familiar tone. It was determined that the form of politeness does not radically alter the overall logic of the model or the set of facts. However, the type of strategy and the choice of tone do influence the depth of analysis and the structure of the argumentation. The research findings demonstrated that polite speech constructions of a neutral tone within the structure of prompts indirectly improve the quality of user interaction with artificial intelligence systems, as they facilitate a clearer, more logical and more structured formulation of queries. Polite expressions serve to indirectly specify the communicative intent, which facilitates the interpretation of the query by the language model and enhances the relevance and meaningfulness of the responses.
References
P. Ribino, “The role of politeness in human–machine interactions: a systematic literature review and future perspectives,” Artif Intell Rev, vol. 56 (Suppl 1), pp. 445-482. 2023. https://doi.org/10.1007/s10462-023-10540-1 .
J-G. Lee, and K. M. Lee, “Polite speech strategies and their impact on drivers’ trust in autonomous vehicles,” Computers in Human Behavior, vol. 127. 2022. https://doi.org/10.1016/j.chb.2021.107015 .
M. Song, H. Zhang, X. Xing, and Y. Duan, “Appreciation vs. apology: Research on the influence mechanism of chatbot service recovery based on politeness theory,” Journal of Retailing and Consumer Services, vol. 73, July 2023. https://doi.org/10.1016/j.jretconser.2023.103323 .
P. Priya, M. Firdaus, and A. Ekbal, “Computational Politeness in Natural Language Processing: A Survey,” ACM Computing Surveys, vol. 56, Issue 9, pp. 1-42. 2024. https://doi.org/10.1145/3654660 .
M. Andruccioli, G. Delnevo, S. Mirri, and P. Salomoni “PromptTone: A Dataset for Evaluating Large Language Model Code Generation Under Varying Prompt Politeness Levels,” Data, vol. 11 (4), 88. 2026. https://doi.org/10.3390/data11040088 .
Z. Yin, H. Wang, K. Horio, D. Kawahara, and S. Sekine, “Should we respect LLMs? A cross-lingual study on the influence of prompt politeness on LLM performance,” Proceedings of the Second Workshop on Social Influence in Conversations, November, рр. 9-35. 2024. https://doi.org/10.18653/v1/2024.sicon-1.2 .
AI Act. Regulation (EU) 2024/1689 of the European Parliament and of the Council. Document 32024R1689. Official Journal of the European Union, 13 June. 2024. URL: https://eur-lex.europa.eu/eli/reg/2024/1689/oj/eng . Accessed: 22.01.2026.
Z. Kornieva, Y. Baklazhenko, and V. Lukianenko, “AI & AIED: Ensuring academic integrity in AI-driven education,” Advanced Education, vol. 19 (27), pp. 4-11. 2025. https://doi.org/10.20535/2410-8286.349020 .
C. A. Yue, L. R. Men, R. Mitson, D. Z. Davis, and A. L. Zhou, “Artificial intelligence for internal communication: Strategies, challenges, and implications,” Public Relations Review, vol. 50. Issue 5. 2024. https://doi.org/10.1016/j.pubrev.2024.102515 .
L. Radomska, and Y. Sulima. “AI Language Models in an Educational Context: An Analysis of Communication Strategies,” Teaching Languages at Higher Educational Establishments at the Present Stage. Intersubject Relations, no. 47, pp. 119-142. 2025. https://doi.org/10.26565/2073-4379-2025-47-08
Downloads
-
pdf (Українська)
Downloads: 0
Published
How to Cite
Issue
Section
License

This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).