The capacity of ChatGPT-4 for L2 writing assessment: A closer look at accuracy, specificity, and relevance
Yazarlar (2)
Doç. Dr. Aysel SARICAOĞLU AYGAN Ankara Sosyal Bilimler Üniversitesi, Türkiye
Doç. Dr. Zeynep Bilki Ted Üniversitesi, Türkiye
| Makale Türü |
Özgün Makale
(SSCI, AHCI, SCI, SCI-Exp dergilerinde yayınlanan tam makale)
|
||
| Dergi Adı | Annual Review of Applied Linguistics (Q1) | ||
| Dergi ISSN | 0267-1905 Wos Dergi Scopus Dergi | ||
| Dergi Tarandığı Indeksler | SSCI | ||
| Makale Dili | İngilizce | Basım Tarihi | 03-2025 |
| Cilt / Sayı / Sayfa | 45 / 1 / 253–273 | DOI | 10.1017/S0267190525100160 |
| Makale Linki | https://doi.org/10.1017/s0267190525100160 | ||
| UAK Araştırma Alanları |
İngiliz Dili Eğitimi
|
||
| Özet |
| This study examined the capacity of ChatGPT-4 to assess L2 writing in an accurate, specific, and relevant way. Based on 35 argumentative essays written by upper-intermediate L2 writers in higher education, we evaluated ChatGPT-4’s assessment capacity across four L2 writing dimensions: (1) Task Response, (2) Coherence and Cohesion, (3) Lexical Resou... |
| Anahtar Kelimeler |
| accuracy | ChatGPT-4 | L2 writing assessment | relevance | specificity |
Science Direct
The capacity of ChatGPT-4 for L2 writing assessment: A closer look at accuracy, specificity, and relevance
BM Sürdürülebilir Kalkınma Amaçları
| Atıf Sayıları | |
| Web of Science | 7 |
| Scopus | 6 |
| Google Scholar | 11 |