View in EDS

Comparing 'ChatGPT' and Authentic Discourse as L2 Academic Speaking Partners: A Corpus-Based Analysis and Exploration of Pedagogical Applicability

Saved in:
Bibliographic Details
Title: Comparing 'ChatGPT' and Authentic Discourse as L2 Academic Speaking Partners: A Corpus-Based Analysis and Exploration of Pedagogical Applicability
Language: English
Authors: Koki Sekitani (ORCID 0009-0003-2965-1464), Masaaki Ogura (ORCID 0000-0003-0703-8741), Takeshi Sato (ORCID 0000-0003-4797-0234)
Source: The EUROCALL Review. 2025 32(2):75-87.
Availability: European Association for Computer-Assisted Language Learning (EUROCALL). EUROCALL Headquarters, School of Modern Languages, University of Ulster, Cromore Road, Coleraine BT52 1SA, Northern Ireland, UK. Tel: +34-67-943-1283; Web site: http://www.eurocall-languages.org/
Peer Reviewed: Y
Page Count: 13
Publication Date: 2025
Document Type: Journal Articles
Reports - Research
Education Level: Higher Education
Postsecondary Education
Descriptors: Artificial Intelligence, Technology Uses in Education, Discourse Analysis, Second Language Learning, Speech Communication, Educational Technology, Transcripts (Written Records), Doctoral Dissertations, Computational Linguistics, Supplementary Reading Materials, Readability, Difficulty Level, Syntax
ISSN: 1695-2618
Abstract: This study examines the extent to which spoken academic English produced by the ChatGPT-4o model (ChatGPT) aligns with authentic discourse and is applicable for use in L2 speaking materials. As generative AI tools gain popularity among L2 learners for speaking practice, it is essential to assess the linguistic and discourse-level validity of such output. Ten dialogues generated by ChatGPT were compared with an authentic transcript of a doctoral dissertation defence from the Michigan Corpus of Academic Spoken English (MICASE) using a corpus linguistic and content analysis approach. Quantitative analyses revealed that ChatGPT produced language with higher lexical diversity, greater use of advanced vocabulary, and more complex syntax than the MICASE sample, but with lower readability. Content analysis showed that while ChatGPT simulated turn-taking and appropriate question-answer sequences, it lacked features of spontaneous interaction such as clarification requests, topic shifts, and overlapping speech. Speaker roles in the generated texts were consistent but followed more scripted and idealized patterns. These findings suggest that ChatGPT can serve as a useful supplementary tool for academic speaking practice, especially in providing structured, high-level input. However, its limitations in simulating authentic interaction highlight the need for guided integration alongside real human dialogue. The study is expected to contribute to the growing body of research on AI-assisted language learning.
Abstractor: As Provided
Entry Date: 2026
Accession Number: EJ1494418
Database: ERIC
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://eric.ed.gov/contentdelivery/servlet/ERICServlet?accno=EJ1494418
    Name: ERIC Full Text
    Category: fullText
    Text: Full Text from ERIC
Header DbId: eric
DbLabel: ERIC
An: EJ1494418
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Comparing 'ChatGPT' and Authentic Discourse as L2 Academic Speaking Partners: A Corpus-Based Analysis and Exploration of Pedagogical Applicability
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Koki+Sekitani%22">Koki Sekitani</searchLink> (ORCID <externalLink term="https://orcid.org/0009-0003-2965-1464">0009-0003-2965-1464</externalLink>)<br /><searchLink fieldCode="AR" term="%22Masaaki+Ogura%22">Masaaki Ogura</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0003-0703-8741">0000-0003-0703-8741</externalLink>)<br /><searchLink fieldCode="AR" term="%22Takeshi+Sato%22">Takeshi Sato</searchLink> (ORCID <externalLink term="https://orcid.org/0000-0003-4797-0234">0000-0003-4797-0234</externalLink>)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="SO" term="%22The+EUROCALL+Review%22"><i>The EUROCALL Review</i></searchLink>. 2025 32(2):75-87.
– Name: Avail
  Label: Availability
  Group: Avail
  Data: European Association for Computer-Assisted Language Learning (EUROCALL). EUROCALL Headquarters, School of Modern Languages, University of Ulster, Cromore Road, Coleraine BT52 1SA, Northern Ireland, UK. Tel: +34-67-943-1283; Web site: http://www.eurocall-languages.org/
– Name: PeerReviewed
  Label: Peer Reviewed
  Group: SrcInfo
  Data: Y
– Name: Pages
  Label: Page Count
  Group: Src
  Data: 13
– Name: DatePubCY
  Label: Publication Date
  Group: Date
  Data: 2025
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Journal Articles<br />Reports - Research
– Name: Audience
  Label: Education Level
  Group: Audnce
  Data: <searchLink fieldCode="EL" term="%22Higher+Education%22">Higher Education</searchLink><br /><searchLink fieldCode="EL" term="%22Postsecondary+Education%22">Postsecondary Education</searchLink>
– Name: Subject
  Label: Descriptors
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Artificial+Intelligence%22">Artificial Intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Technology+Uses+in+Education%22">Technology Uses in Education</searchLink><br /><searchLink fieldCode="DE" term="%22Discourse+Analysis%22">Discourse Analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Second+Language+Learning%22">Second Language Learning</searchLink><br /><searchLink fieldCode="DE" term="%22Speech+Communication%22">Speech Communication</searchLink><br /><searchLink fieldCode="DE" term="%22Educational+Technology%22">Educational Technology</searchLink><br /><searchLink fieldCode="DE" term="%22Transcripts+%28Written+Records%29%22">Transcripts (Written Records)</searchLink><br /><searchLink fieldCode="DE" term="%22Doctoral+Dissertations%22">Doctoral Dissertations</searchLink><br /><searchLink fieldCode="DE" term="%22Computational+Linguistics%22">Computational Linguistics</searchLink><br /><searchLink fieldCode="DE" term="%22Supplementary+Reading+Materials%22">Supplementary Reading Materials</searchLink><br /><searchLink fieldCode="DE" term="%22Readability%22">Readability</searchLink><br /><searchLink fieldCode="DE" term="%22Difficulty+Level%22">Difficulty Level</searchLink><br /><searchLink fieldCode="DE" term="%22Syntax%22">Syntax</searchLink>
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 1695-2618
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This study examines the extent to which spoken academic English produced by the ChatGPT-4o model (ChatGPT) aligns with authentic discourse and is applicable for use in L2 speaking materials. As generative AI tools gain popularity among L2 learners for speaking practice, it is essential to assess the linguistic and discourse-level validity of such output. Ten dialogues generated by ChatGPT were compared with an authentic transcript of a doctoral dissertation defence from the Michigan Corpus of Academic Spoken English (MICASE) using a corpus linguistic and content analysis approach. Quantitative analyses revealed that ChatGPT produced language with higher lexical diversity, greater use of advanced vocabulary, and more complex syntax than the MICASE sample, but with lower readability. Content analysis showed that while ChatGPT simulated turn-taking and appropriate question-answer sequences, it lacked features of spontaneous interaction such as clarification requests, topic shifts, and overlapping speech. Speaker roles in the generated texts were consistent but followed more scripted and idealized patterns. These findings suggest that ChatGPT can serve as a useful supplementary tool for academic speaking practice, especially in providing structured, high-level input. However, its limitations in simulating authentic interaction highlight the need for guided integration alongside real human dialogue. The study is expected to contribute to the growing body of research on AI-assisted language learning.
– Name: AbstractInfo
  Label: Abstractor
  Group: Ab
  Data: As Provided
– Name: DateEntry
  Label: Entry Date
  Group: Date
  Data: 2026
– Name: AN
  Label: Accession Number
  Group: ID
  Data: EJ1494418
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=EJ1494418
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 13
        StartPage: 75
    Subjects:
      – SubjectFull: Artificial Intelligence
        Type: general
      – SubjectFull: Technology Uses in Education
        Type: general
      – SubjectFull: Discourse Analysis
        Type: general
      – SubjectFull: Second Language Learning
        Type: general
      – SubjectFull: Speech Communication
        Type: general
      – SubjectFull: Educational Technology
        Type: general
      – SubjectFull: Transcripts (Written Records)
        Type: general
      – SubjectFull: Doctoral Dissertations
        Type: general
      – SubjectFull: Computational Linguistics
        Type: general
      – SubjectFull: Supplementary Reading Materials
        Type: general
      – SubjectFull: Readability
        Type: general
      – SubjectFull: Difficulty Level
        Type: general
      – SubjectFull: Syntax
        Type: general
    Titles:
      – TitleFull: Comparing 'ChatGPT' and Authentic Discourse as L2 Academic Speaking Partners: A Corpus-Based Analysis and Exploration of Pedagogical Applicability
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Koki Sekitani
      – PersonEntity:
          Name:
            NameFull: Masaaki Ogura
      – PersonEntity:
          Name:
            NameFull: Takeshi Sato
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-electronic
              Value: 1695-2618
          Numbering:
            – Type: volume
              Value: 32
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: The EUROCALL Review
              Type: main
ResultId 1