Articles producció científicaFilologies Romàniques

Intelligent (but artificial) Feedback in Spanish as a Foreign Language: Evaluation of ChatGPT and Claude as Text Correction Tools

  • Dades identificatives

    Identificador:  imarina:9498462
    Handle: https://hdl.handle.net/20.500.11797/imarina9498462
    Autors:  Antoni Brosa Rodríguez
    Resum:
    This research analyses the potential and limitations of two artificial intelligence models (ChatGPT 4 and Claude 3.7) as feedback tools for texts written by students of Spanish as a foreign language. Using selected texts from the CEDEL2 corpus, the study evaluates these models' ability to provide pedagogically appropriate corrections. The qualitative analysis focuses on four criteria: accuracy in error detection, clarity of explanations, pedagogical adequacy, and potential problems. Results reveal that both models show high precision in detecting basic errors but present significant limitations such as overcorrection and difficulties adapting explanations to the student's level. Claude stands out for its systematic structure, while ChatGPT excels in humanizing feedback. Based on these findings, we propose an integrated model to implement these tools in the Spanish language classroom, where the teacher maintains a crucial role as mediator, and we offer practical recommendations to maximize their benefits while minimizing their risks.

  • Altres:

    Autor segons l'article: Antoni Brosa Rodríguez
    Versió de l'article dipositat: info:eu-repo/semantics/publishedVersion
    Enllaç font original: https://polipapers.upv.es/index.php/eurocall/article/view/23827
    Departament: Filologies Romàniques
    Autor/s de la URV: Antoni Brosa Rodríguez
    DOI de l'article: 10.4995/eurocall.2025.23827
    Resum: This research analyses the potential and limitations of two artificial intelligence models (ChatGPT 4 and Claude 3.7) as feedback tools for texts written by students of Spanish as a foreign language. Using selected texts from the CEDEL2 corpus, the study evaluates these models' ability to provide pedagogically appropriate corrections. The qualitative analysis focuses on four criteria: accuracy in error detection, clarity of explanations, pedagogical adequacy, and potential problems. Results reveal that both models show high precision in detecting basic errors but present significant limitations such as overcorrection and difficulties adapting explanations to the student's level. Claude stands out for its systematic structure, while ChatGPT excels in humanizing feedback. Based on these findings, we propose an integrated model to implement these tools in the Spanish language classroom, where the teacher maintains a crucial role as mediator, and we offer practical recommendations to maximize their benefits while minimizing their risks.
    Any de publicació de la revista: 2025
    Accès a la llicència d'ús: https://creativecommons.org/licenses/by/3.0/es/
    Adreça de correu electrònic de l'autor: antoni.brosa@urv.cat