Truace
Subscribe
70/100

Moderate evidence

Cite
More
Export CSVExport JSONEmailLinkedInX

Polite prompts made Korean students like ChatGPT more, a 43-person experiment finds

Study title: Prompting with Respect: Cultural Norms and User Experience in LLM Interactions

Evidence type
Randomized controlled trial
Sample
n = 43
Sources
1 sourcePeer-reviewed
Published
2 min read
Truvace record
TRV-2026-2679cite or check it

Study title: Prompting with Respect: Cultural Norms and User Experience in LLM Interactions

A controlled experiment with 43 Korean female college students tested whether the tone of their prompts changed how they felt about ChatGPT. Half wrote respectful prompts with polite requests, compliments and gratitude; the others wrote directive prompts using imperatives, criticism and performance-based penalties. All completed a writing task with ChatGPT.

Read the study 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 p…

The gain

In a randomized experiment with 43 Korean female college students, those who wrote polite, grateful prompts to ChatGPT reported significantly higher satisfaction, especially affinity and likability, than those who used imperatives and criticism.

In brief

Respectful prompting produced significantly higher satisfaction, particularly affinity and likability. Perceived output quality differed less between groups, and that difference was not significant. So the tone shaped how users felt about the exchange more than how good they judged the writing.

ChatGPT also responded differently: respectful prompts drew socially supportive replies, while directive prompts were followed by apologies. The authors read this as two-way social adaptation between users and the chatbot, and argue that language models should be designed to recognise different cultural communication patterns.

Main points

  1. Forty-three Korean female college students were randomly assigned to respectful or directive prompting.
  2. Respectful prompts used polite requests, compliments and gratitude; directive prompts used imperatives, criticism and performance-based penalties.
  3. Participants completed a writing task using ChatGPT.
  4. Satisfaction was significantly higher with respectful prompts, especially affinity and likability.
  5. The difference in perceived output quality was smaller and not significant.
  6. ChatGPT gave socially supportive responses to respectful prompts and apologies after directive ones.

The full story

The experiment focused on a contrast that carries cultural meaning in Korean: respectful versus directive speech. Researchers wanted to know how this affects users' psychological experience with a large language model, an area they describe as largely unexplored despite interest in prompt engineering.

Participants were randomly assigned to one of two conditions and did a writing task with ChatGPT. Satisfaction ratings favoured respectful prompting, with the clearest gaps in affinity and likability, while ratings of output quality did not differ significantly.

The chatbot's replies also varied by tone. Polite prompts were met with socially supportive responses, and harsh prompts with apologies. The authors conclude that culturally grounded conventions can shape subjective experience even when perceived output quality is similar, and recommend culturally adaptive system design.

Sources

1 on file
  1. Cyberpsychology, Behavior, and Social Networkingdoi:10.1177/21522715261484255
    Peer-reviewed2026-09-11

Talk it over

Four questions to start onWho gets this benefit, and who was left out of the study or story?

Start with a question

Polite prompts made Korean students like ChatGPT more, a 43-person experiment findshttps://truvace.com/item/prompting-with-respect-cultural-norms-and-user-experience-in-llm-interactions

  1. Who gets this benefit, and who was left out of the study or story?

    The gain In a randomized experiment with 43 Korean female college students, those who wrote polite, grateful prompts to ChatGPT reported significantly higher satisfaction, especially affinity and likability, than those who used imperatives and criticism.

    Answer in the thread

  2. How do we know? What can this kind of evidence show, and what can’t it?

    The evidence This rests on a randomized controlled trial with a sample of 43, from Cyberpsychology, Behavior, and Social Networking.

    Answer in the thread

  3. What does it leave open? What else would you want to know before acting on it?

    The record’s own caveat The experiment involved only 43 Korean female college students on a single writing task, which limits how far the results extend to other groups, languages or tasks.

    Answer in the thread

  4. Have you seen AI used this way where you study, work or live? Did it go the same way?

    Answer in the thread

The questions are the same on every record. The details under them are taken from this record as written.

What readers say

More from Lifestyle