Sep 2026· Cyberpsychology, Behavior, and Social Networking· Vol 29, pp. 746 - 753· 0 citations· 22 references
Medicine
Abstract
Despite growing interest in prompt engineering, its influence on user experience—particularly in relation to cultural communication norms—remains largely unexplored. This controlled experiment examined how respectful versus directive prompting—a culturally meaningful contrast in Korean—affects Korean users’ psychological experience during LLM interactions. Forty-three Korean female college students were randomly assigned to respectful prompt (RP) (using polite requests, compliments, and gratitude) or directive prompt (DP) (using imperatives, criticism, and performance-based penalties) conditions. Participants completed a writing task using ChatGPT. Results indicated that RPs yielded significantly higher satisfaction, particularly for affinity and likability, whereas the difference in perceived output quality was smaller and nonsignificant. Furthermore, RPs elicited socially supportive ChatGPT responses, whereas DPs were followed by apologies, suggesting bidirectional social adaptation between users and ChatGPT. Together, these findings suggest that culturally grounded communicative conventions may shape users’ subjective experience even where perceived output quality does not differ significantly, pointing to culturally adaptive large language model systems that recognize diverse communication patterns as essential design considerations rather than imposing universal paradigms.
Gratitude technologies support well-being by prompting reflection on what people appreciate. But gratitude does not serve the same purpose in every circumstance: as life situations change, so does what people seek from it, and whether it feels appropriate at all. To understand how technology can adapt to and support su...
Joy Qiuyue Zhong, Jeongah Lee, Drishti Goel et al.· 0 citations
This Work-in-Progress examines whether personality-informed prompting changes perceived LLM emotional support in driving scenarios designed to elicit stress. A condition-order-balanced, within-subject CARLA simulator study (n = 14) compared a baseline with a Driver Personality Profile (DPP) condition; a supplementary o...
Max Mittelstädt, Ece Sutanrikulu, Lumbardh Ljatifi et al.· International Conference on...· 0 citations
The results show that students' cognitive engagement is not passive information reception, but rather manifested as self-regulatory strategies, which confirms that learning engagement in virtual communication is neither a natural occurrence nor a result driven by technology, but a dynamic process influenced by multiple...
Rongpu Ma· Lecture Notes in Education P...· 0 citations
This study investigates how positive teacher interpersonal communication behaviors operate when learner error places face at risk in real-time L2 classroom interaction. It reframes error correction as a relational event rather than a purely linguistic or cognitive one, examining the conditions under which correction ca...
Ebru Boynueğri, Nuray Alagözlü· HAYEF Journal of Education· 0 citations
Purpose – This study explores how Indonesian EFL students experience evaluative conditions during AI-mediated speaking practice, utilize feedback and repeated practice opportunities, and perceive the transfer of comfort and confidence from AI interactions to communication with humans.
Methodology – This interpretive q...
Budiawan Budiawan· Journal of Literature Langua...· 0 citations
Related blog posts
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT scientists developed a training method to generate models that simulate the effects of human activities on climate much more quickly than other approaches.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.