Can artificial intelligence read our handwriting? A comparison of humans and artificial intelligence in the future of assessment

İsmail Yaşartürk, Halil İbrahim Öksüz, Ramazan Deniz and Mustafa Öztürk

PLOS ONE, 2026, vol. 21, issue 9, 1-14

Abstract: The purpose of this study is to evaluate the legibility of fourth-grade elementary school students’ handwriting and to examine the differences and relationships between two evaluators: a human researcher and artificial intelligence (ChatGPT). To this end, the study was conducted using the descriptive survey model, one of the quantitative research approaches. The study sample consisted of 67 fourth-grade students attending a public elementary school. The students’ handwriting was evaluated using the Multidimensional Legibility Scale. Writing samples were collected from each student, including copying samples, dictated samples, and free writing samples. One class period was allocated for each writing task. The 201 handwriting samples obtained from the 67 students were evaluated by a researcher (the second author) and artificial intelligence (ChatGPT). According to the findings, no significant differences were detected between the artificial intelligence and the researcher in any writing type or subdimension, except for the slant subdimension of free writing. However, a high level of positive and significant correlation was identified between the two raters. Findings indicate that artificial intelligence can produce results comparable to those of expert raters when evaluating handwriting legibility. The fact that differences among raters are not statistically significant suggests that AI-based handwriting evaluations could serve as an objective and reliable alternative.

Date: 2026
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0358694 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 58694&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0358694

DOI: 10.1371/journal.pone.0358694

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().