Academic Journal
Προβολή σε EDS

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

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Prompting with Respect: Cultural Norms and User Experience in LLM Interactions.
Συγγραφείς: Yang S; Department of Psychology, Ewha Womans University, Seoul, Republic of Korea., Oh S; Department of Psychology, Ewha Womans University, Seoul, Republic of Korea., Shim HE; Department of Psychology, Ewha Womans University, Seoul, Republic of Korea.
Πηγή: Cyberpsychology, behavior and social networking [Cyberpsychol Behav Soc Netw] 2026 Oct; Vol. 29 (10), pp. 746-753. Date of Electronic Publication: 2026 Sep 11.
Τύπος έκδοσης: Journal Article
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: Mary Ann Liebert, Inc Country of Publication: United States NLM ID: 101528721 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 2152-2723 (Electronic) Linking ISSN: 21522715 NLM ISO Abbreviation: Cyberpsychol Behav Soc Netw Subsets: MEDLINE
Imprint Name(s): Original Publication: New Rochelle, NY : Mary Ann Liebert, Inc.
Ιατρικοί όροι (MeSH): Large Language Models* , Communication* , Social Norms* , Social Interaction* , Interpersonal Relations*, Humans ; Female ; Young Adult ; Adult ; Republic of Korea
Περίληψη: 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.
Competing Interests: Author Disclosure StatementThe authors declared no potential conflicts of interest with respect to the research, authorship, and publication of this article.
Contributed Indexing: Keywords: ChatGPT; communication patterns; cultural norms; large language models; prompt engineering; user satisfaction
Entry Date(s): Date Created: 20260911 Date Completed: 20260928 Latest Revision: 20260928
Update Code: 20260928
DOI: 10.1177/21522715261484255
PMID: 42723560
Βάση Δεδομένων: MEDLINE
FullText Text:
  Availability: 0
Header DbId: cmedm
DbLabel: MEDLINE
An: 42723560
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Prompting with Respect: Cultural Norms and User Experience in LLM Interactions.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Yang+S%22">Yang S</searchLink>; Department of Psychology, Ewha Womans University, Seoul, Republic of Korea.<br /><searchLink fieldCode="AU" term="%22Oh+S%22">Oh S</searchLink>; Department of Psychology, Ewha Womans University, Seoul, Republic of Korea.<br /><searchLink fieldCode="AU" term="%22Shim+HE%22">Shim HE</searchLink>; Department of Psychology, Ewha Womans University, Seoul, Republic of Korea.
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22101528721%22">Cyberpsychology, behavior and social networking</searchLink> [Cyberpsychol Behav Soc Netw] 2026 Oct; Vol. 29 (10), pp. 746-753. <i>Date of Electronic Publication: </i>2026 Sep 11.
– Name: TypePub
  Label: Publication Type
  Group: TypPub
  Data: Journal Article
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: TitleSource
  Label: Journal Info
  Group: Src
  Data: <i>Publisher: </i><searchLink fieldCode="PB" term="%22Mary+Ann+Liebert%2C+Inc%22">Mary Ann Liebert, Inc </searchLink><i>Country of Publication: </i>United States <i>NLM ID: </i>101528721 <i>Publication Model: </i>Print-Electronic <i>Cited Medium: </i>Internet <i>ISSN: </i>2152-2723 (Electronic) <i>Linking ISSN: </i><searchLink fieldCode="IS" term="%2221522715%22">21522715 </searchLink><i>NLM ISO Abbreviation: </i>Cyberpsychol Behav Soc Netw <i>Subsets: </i>MEDLINE
– Name: PublisherInfo
  Label: Imprint Name(s)
  Group: PubInfo
  Data: <i>Original Publication</i>: New Rochelle, NY : Mary Ann Liebert, Inc.
– Name: SubjectMESH
  Label: MeSH Terms
  Group: Su
  Data: <searchLink fieldCode="MM" term="%22Large+Language+Models%22">Large Language Models*</searchLink> <br /><searchLink fieldCode="MM" term="%22Communication%22">Communication*</searchLink> <br /><searchLink fieldCode="MM" term="%22Social+Norms%22">Social Norms*</searchLink> <br /><searchLink fieldCode="MM" term="%22Social+Interaction%22">Social Interaction*</searchLink> <br /><searchLink fieldCode="MM" term="%22Interpersonal+Relations%22">Interpersonal Relations*</searchLink><br /><searchLink fieldCode="MH" term="%22Humans%22">Humans</searchLink> ; <searchLink fieldCode="MH" term="%22Female%22">Female</searchLink> ; <searchLink fieldCode="MH" term="%22Young+Adult%22">Young Adult</searchLink> ; <searchLink fieldCode="MH" term="%22Adult%22">Adult</searchLink> ; <searchLink fieldCode="MH" term="%22Republic+of+Korea%22">Republic of Korea</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: 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.
– Name: Abstract
  Label: Competing Interests
  Group: Ab
  Data: Author Disclosure StatementThe authors declared no potential conflicts of interest with respect to the research, authorship, and publication of this article.
– Name: SubjectMinor
  Label: Contributed Indexing
  Group:
  Data: <i>Keywords: </i>ChatGPT; communication patterns; cultural norms; large language models; prompt engineering; user satisfaction
– Name: DateEntry
  Label: Entry Date(s)
  Group: Date
  Data: <i>Date Created: </i>20260911 <i>Date Completed: </i>20260928 <i>Latest Revision: </i>20260928
– Name: DateUpdate
  Label: Update Code
  Group: Date
  Data: 20260928
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1177/21522715261484255
– Name: AN
  Label: PMID
  Group: ID
  Data: 42723560
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=cmedm&AN=42723560
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1177/21522715261484255
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        StartPage: 746
    Subjects:
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Female
        Type: general
      – SubjectFull: Young Adult
        Type: general
      – SubjectFull: Adult
        Type: general
      – SubjectFull: Republic of Korea
        Type: general
      – SubjectFull: Large Language Models
        Type: general
      – SubjectFull: Communication
        Type: general
      – SubjectFull: Social Norms
        Type: general
      – SubjectFull: Social Interaction
        Type: general
      – SubjectFull: Interpersonal Relations
        Type: general
    Titles:
      – TitleFull: Prompting with Respect: Cultural Norms and User Experience in LLM Interactions.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Yang S
      – PersonEntity:
          Name:
            NameFull: Oh S
      – PersonEntity:
          Name:
            NameFull: Shim HE
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: 2026 Oct
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-electronic
              Value: 2152-2723
          Numbering:
            – Type: volume
              Value: 29
            – Type: issue
              Value: 10
          Titles:
            – TitleFull: Cyberpsychology, behavior and social networking
              Type: main
ResultId 1