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, Mustafa Öztürk · 2026

Read Can artificial intelligence read our handwriting? A comparison of humans and artificial intelligence in the future of assessment by İsmail Yaşartürk, Halil İbrahim Öksüz, Ramazan Deniz, Mustafa Öztürk (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0358694.txt.

Description

İsmail Yaşartürk leads a team of four asking whether artificial intelligence can judge children's handwriting as fairly as a human expert, in PLOS ONE in 2026. Sixty-seven fourth graders at a public school produced copying, dictation, and free writing samples, two hundred one pieces. Each was scored on a multidimensional legibility scale twice, once by a researcher and once by ChatGPT, and the two sets of marks were compared dimension by dimension.

Across writing types and scoring dimensions, the artificial intelligence and the human produced no significant differences, with one exception: the slant score in free writing. Their marks correlated strongly and positively. The authors read this as evidence that automated scoring can match expert judgment for handwriting legibility, which could lighten a tedious assessment burden in crowded classrooms. They frame the tool as an assistant to teachers, whose knowledge of each child no scale captures.

Catalog record

CREATORİsmail Yaşartürk, Halil İbrahim Öksüz, Ramazan Deniz, Mustafa Öztürk
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE41957
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0358694

Browse the full library · About the Tower of Babel