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, Yasir Abdullah · 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, Yasir Abdullah (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/PMC13592574.txt.
Description
İsmail Yaşartürk and four colleagues ask whether artificial intelligence can grade children's handwriting as fairly as a human expert. Their sample held 67 fourth grade pupils at a public school, each producing three kinds of writing: copied, dictated, and free. That gave 201 samples, scored on a multidimensional legibility scale by one researcher and by ChatGPT working from the same scale.
Across nearly every writing type and sub score, the two raters showed no meaningful gap. Their scores also correlated strongly and positively. The lone exception was slant in free writing. Yaşartürk and the team conclude that AI grading of legibility can match expert grading closely enough to serve as an objective aid, easing a heavy teacher workload.
Catalog record
| CREATOR | İsmail Yaşartürk, Halil İbrahim Öksüz, Ramazan Deniz, Mustafa Öztürk, Yasir Abdullah |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 40 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |