This study investigates the use of ChatGPT for Automated Essay Scoring (AES) in assessing Italian middle school students’ written texts. Using rubrics targeting grammar, coherence and argumentation, we compare AI-generated feedback with that of a human teacher on a newly collected corpus of students’ essays. Despite some differences, ChatGPT provided detailed and timely feedback that complements the teacher’s role. These findings underscore the potential of generative AI to improve the assessment of writing, providing useful insights for educators and supporting students in developing their writing skills.
Exploring LLM-Based Assessment of Italian Middle School Writing: A Pilot Study
Brunato, Dominique Pierina
2025
Abstract
This study investigates the use of ChatGPT for Automated Essay Scoring (AES) in assessing Italian middle school students’ written texts. Using rubrics targeting grammar, coherence and argumentation, we compare AI-generated feedback with that of a human teacher on a newly collected corpus of students’ essays. Despite some differences, ChatGPT provided detailed and timely feedback that complements the teacher’s role. These findings underscore the potential of generative AI to improve the assessment of writing, providing useful insights for educators and supporting students in developing their writing skills.| Campo DC | Valore | Lingua |
|---|---|---|
| dc.authority.orgunit | Istituto di linguistica computazionale "Antonio Zampolli" - ILC | en |
| dc.authority.people | Mirabella, Adriana | en |
| dc.authority.people | Brunato, Dominique Pierina | en |
| dc.collection.id.s | 71c7200a-7c5f-4e83-8d57-d3d2ba88f40d | * |
| dc.collection.name | 04.01 Contributo in Atti di convegno | * |
| dc.contributor.appartenenza | Istituto di linguistica computazionale "Antonio Zampolli" - ILC | * |
| dc.contributor.appartenenza.mi | 918 | * |
| dc.contributor.area | Non assegn | * |
| dc.date.accessioned | 2026/03/03 12:15:09 | - |
| dc.date.available | 2026/03/03 12:15:09 | - |
| dc.date.firstsubmission | 2026/03/03 09:38:01 | * |
| dc.date.issued | 2025 | - |
| dc.date.submission | 2026/03/03 09:38:01 | * |
| dc.description.abstracteng | This study investigates the use of ChatGPT for Automated Essay Scoring (AES) in assessing Italian middle school students’ written texts. Using rubrics targeting grammar, coherence and argumentation, we compare AI-generated feedback with that of a human teacher on a newly collected corpus of students’ essays. Despite some differences, ChatGPT provided detailed and timely feedback that complements the teacher’s role. These findings underscore the potential of generative AI to improve the assessment of writing, providing useful insights for educators and supporting students in developing their writing skills. | - |
| dc.description.allpeople | Mirabella, Adriana; Brunato, Dominique Pierina | - |
| dc.description.allpeopleoriginal | Mirabella, Adriana; Brunato, Dominique Pierina | en |
| dc.description.fulltext | open | en |
| dc.description.international | no | en |
| dc.description.numberofauthors | 2 | - |
| dc.identifier.doi | 10.18653/v1/2025.bea-1.51 | en |
| dc.identifier.source | crossref | * |
| dc.identifier.uri | https://hdl.handle.net/20.500.14243/570561 | - |
| dc.identifier.url | https://aclanthology.org/2025.bea-1.51/ | en |
| dc.language.iso | eng | en |
| dc.publisher.name | Association for Computational Linguistics. | en |
| dc.relation.firstpage | 708 | en |
| dc.relation.ispartofbook | Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025) | en |
| dc.relation.lastpage | 715 | en |
| dc.relation.numberofpages | 8 | en |
| dc.subject.keywordseng | automated essay scoring, LLM, Italian learners, argumentative essays | - |
| dc.subject.singlekeyword | automated essay scoring | * |
| dc.subject.singlekeyword | LLM | * |
| dc.subject.singlekeyword | Italian learners | * |
| dc.subject.singlekeyword | argumentative essays | * |
| dc.title | Exploring LLM-Based Assessment of Italian Middle School Writing: A Pilot Study | en |
| dc.type.driver | info:eu-repo/semantics/conferenceObject | - |
| dc.type.full | 04 Contributo in convegno::04.01 Contributo in Atti di convegno | it |
| dc.type.miur | 273 | - |
| iris.mediafilter.data | 2026/03/04 02:52:18 | * |
| iris.orcid.lastModifiedDate | 2026/03/03 12:15:09 | * |
| iris.orcid.lastModifiedMillisecond | 1772536509061 | * |
| iris.sitodocente.maxattempts | 1 | - |
| iris.unpaywall.bestoaversion | publishedVersion | * |
| iris.unpaywall.doi | 10.18653/v1/2025.bea-1.51 | * |
| iris.unpaywall.isoa | true | * |
| iris.unpaywall.landingpage | https://doi.org/10.18653/v1/2025.bea-1.51 | * |
| iris.unpaywall.license | cc-by | * |
| iris.unpaywall.metadataCallLastModified | 04/03/2026 04:34:28 | - |
| iris.unpaywall.metadataCallLastModifiedMillisecond | 1772595268916 | - |
| iris.unpaywall.oastatus | gold | * |
| iris.unpaywall.pdfurl | https://aclanthology.org/2025.bea-1.51.pdf | * |
| Appare nelle tipologie: | 04.01 Contributo in Atti di convegno | |
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
2025.bea-1.51.pdf
accesso aperto
Descrizione: pdf dell'articolo pubblicato
Tipologia:
Versione Editoriale (PDF)
Licenza:
Creative commons
Dimensione
112.36 kB
Formato
Adobe PDF
|
112.36 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
