Human raters vs Chat GPT : how do their scorings of EFL learners’ academic writing differ?

Vista sencilla de ítem
dc.contributor.advisorGuapacha Chamorro, María Eugenia
dc.contributor.authorZapata Villano, Valentina
dc.date.accessioned2026-01-21T17:48:10Z
dc.date.available2026-01-21T17:48:10Z
dc.date.issued2025
dc.description.abstractArtificial Intelligence (AI) in language assessment has gained attention due to its potential to minimize teachers’ complex task of assessing students’ writing. Although previous research has explored the use of technological tools to assess EFL learners’ writing, there is a need to further investigate how AI, particularly ChatGPT, can be used as an assessment tool in high-stakes writing assessment, and whether the scores provided by the AI are similar to those assigned by human raters. In the context of a high-stakes writing test at Universidad del Valle, this quantitative research investigated how the scorings of EFL university teachers differed from those given by ChatGPT when assessing EFL university learners’ written productions (personal opinion essay and data explanatory essay). Two argumentative writing tasks from two cohorts of ninth-semester EFL learners (N= 208) were used to compare the global and analytic ratings awarded by a pool of 20 human raters with those of ChatGPT using an analytic scoring rubric. The analytic dimensions included content, coherence and cohesion, sentence structure, grammar, and vocabulary. A total of 7072 scores were analyzed, including 416 global (208 human and 208 ChatGPT) and 6656 analytic scores across two writing tasks. Analytic scoring covered seven criteria for Task 1 and nine for Task 2, with both human raters and ChatGPT providing an equal number of ratings (3328 each). Data were analyzed on JASP, by using correlations and paired-samples t-test. According to the results, ChatGPT showed moderate agreement with human raters in surface-level dimensions such as grammar, vocabulary, and sentence structure.eng
dc.description.degreelevelPregradospa
dc.description.degreenameLICENCIADO(A) EN LENGUAS EXTRANJERAS INGLÉS - FRANCÉSspa
dc.format.extent1 recurso en linea (69 páginas)
dc.format.mimetypeapplication/pdf
dc.identifier.urihttps://hdl.handle.net/10893/39074
dc.language.isoeng
dc.publisherUniversidad del Vallespa
dc.publisher.branchSede Cali
dc.publisher.facultyFACULTAD DE HUMANIDADESspa
dc.publisher.placeColombiaspa
dc.publisher.programLICENCIATURA EN LENGUAS EXTRANJERAS INGLÉS - FRANCÉSspa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.coarhttp://purl.org/coar/access_right/c_abf2spa
dc.rights.licenseAtribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0)spa
dc.subject.lembEFL
dc.subject.lembChatGPT
dc.subject.lembEvaluadores humanos
dc.subject.lembEducación con IA
dc.subject.lembEvaluación de escritura EFL
dc.subject.lembEvaluación de escritura basada en IA
dc.subject.lembEstudiantes de lenguas extranjeras
dc.titleHuman raters vs Chat GPT : how do their scorings of EFL learners’ academic writing differ?eng
dc.typeTrabajo de grado - Pregradospa
dc.type.coarhttp://purl.org/coar/resource_type/c_7a1f
dc.type.coarversionhttp://purl.org/coar/version/c_970fb48d4fbd8a85spa
dc.type.contentText
dc.type.driverinfo:eu-repo/semantics/bachelorThesis
dc.type.redcolhttp://purl.org/redcol/resource_type/TP
dc.type.versioninfo:eu-repo/semantics/publishedVersionspa
dspace.entity.typePublication
Archivos
Bloque original
Mostrando 1 - 2 de 2
Miniatura
Nombre:
3267 Z35h.pdf
Tamaño:
754.6 KB
Formato:
Adobe Portable Document Format
Descargar
No hay miniatura disponible
Nombre:
Autorizacion-1192713135.pdf
Tamaño:
984.5 KB
Formato:
Adobe Portable Document Format
Descargar
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
15.18 KB
Formato:
Item-specific license agreed upon to submission
Descripción:
Descargar
Colecciones
Licenciatura en Lenguas Extranjeras Inglés-Francés