Reading the Readers Mind through Eye Tracking: Can AI Generated Texts Match Human Authors?

Chaudhary Muhammad Aqdus Ilyas; Sifat-E Noor; Ashkan  Tashk; Bart Cooreman; Sofie Beier; Per Bækgaard

doi:10.1145/3715669.3726846

Reading the Readers Mind through Eye Tracking: Can AI Generated Texts Match Human Authors?

Chaudhary Muhammad Aqdus Ilyas
, Sifat-E Noor
, Ashkan Tashk
, Bart Cooreman
, Sofie Beier
, Per Bækgaard

Publications: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

While Generative AI models like Large Language Models (LLMs)
are capable of generating extensive text, their efficacy in producing
readable content for human participants in experimental settings
remains to be evaluated. Further, eye-tracking technology is increas-
ingly utilized to study cognition and behavior, yet its application to
readers’ cognitive processes when exposed to AI-generated versus
human-authored texts remains unexplored. This study investigates
how text generated by LLMs influences reading by analyzing gaze
patterns.
The study collects gaze data from 13 participants as they read AI-
generated and human-authored passages. A comparative analysis is
conducted within subjects to assess gaze patterns between authors
and between text types based on the robust two-means clustering
(I2MC) algorithm to identify fixations. In addition, pupil dilation
and reading speed were examined.
Our findings reveal significant differences in fixation character-
istics not only between authors but also between AI-generated and
human-authored texts.

Original language	English
Title of host publication	Proceedings of the 2025 Symposium on Eye Tracking Research and Applications (ETRA '25)
Place of Publication	Association for Computing Machinery
Publication date	2025
Pages	1-7
Article number	113
DOIs	https://doi.org/10.1145/3715669.3726846
Publication status	Published - 2025
Event	ETRA: 2025 Symposium on Eye Tracking Research and Applications - Tokyo, Japan Duration: 26 May 2025 → 29 May 2025 https://etra.acm.org/2025/

Conference

Conference	ETRA
Country/Territory	Japan
City	Tokyo
Period	26/05/2025 → 29/05/2025
Internet address	https://etra.acm.org/2025/

Keywords

Eye-tracking
Fixation detection
AI and Human authored reading patterns

Artistic research

No

Access to Document

10.1145/3715669.3726846

Cite this

@inproceedings{aed8e407b90c4717b8b66bc8873be021,

title = "Reading the Readers Mind through Eye Tracking: Can AI Generated Texts Match Human Authors?",

abstract = "While Generative AI models like Large Language Models (LLMs) are capable of generating extensive text, their efficacy in producing readable content for human participants in experimental settings remains to be evaluated. Further, eye-tracking technology is increas- ingly utilized to study cognition and behavior, yet its application to readers{\textquoteright} cognitive processes when exposed to AI-generated versus human-authored texts remains unexplored. This study investigates how text generated by LLMs influences reading by analyzing gaze patterns. The study collects gaze data from 13 participants as they read AI- generated and human-authored passages. A comparative analysis is conducted within subjects to assess gaze patterns between authors and between text types based on the robust two-means clustering (I2MC) algorithm to identify fixations. In addition, pupil dilation and reading speed were examined. Our findings reveal significant differences in fixation character- istics not only between authors but also between AI-generated and human-authored texts.",

keywords = "Eye-tracking, Fixation detection, AI and Human authored reading patterns",

author = "Ilyas, \{Chaudhary Muhammad Aqdus\} and Sifat-E Noor and Ashkan Tashk and Bart Cooreman and Sofie Beier and Per B{\ae}kgaard",

year = "2025",

doi = "10.1145/3715669.3726846",

language = "English",

pages = "1--7",

booktitle = "Proceedings of the 2025 Symposium on Eye Tracking Research and Applications (ETRA '25)",

note = "ETRA : 2025 Symposium on Eye Tracking Research and Applications ; Conference date: 26-05-2025 Through 29-05-2025",

url = "https://etra.acm.org/2025/",

}

Ilyas, CMA, Noor, S-E, Tashk, A, Cooreman, B , Beier, S & Bækgaard, P 2025, Reading the Readers Mind through Eye Tracking: Can AI Generated Texts Match Human Authors? in Proceedings of the 2025 Symposium on Eye Tracking Research and Applications (ETRA '25)., 113, Association for Computing Machinery, pp. 1-7, ETRA, Tokyo, Japan, 26/05/2025. https://doi.org/10.1145/3715669.3726846

Reading the Readers Mind through Eye Tracking: Can AI Generated Texts Match Human Authors? / Ilyas, Chaudhary Muhammad Aqdus; Noor, Sifat-E; Tashk, Ashkan et al.
Proceedings of the 2025 Symposium on Eye Tracking Research and Applications (ETRA '25). Association for Computing Machinery, 2025. p. 1-7 113.

Publications: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Reading the Readers Mind through Eye Tracking

T2 - ETRA

AU - Ilyas, Chaudhary Muhammad Aqdus

AU - Noor, Sifat-E

AU - Tashk, Ashkan

AU - Cooreman, Bart

AU - Beier, Sofie

AU - Bækgaard, Per

PY - 2025

Y1 - 2025

N2 - While Generative AI models like Large Language Models (LLMs) are capable of generating extensive text, their efficacy in producing readable content for human participants in experimental settings remains to be evaluated. Further, eye-tracking technology is increas- ingly utilized to study cognition and behavior, yet its application to readers’ cognitive processes when exposed to AI-generated versus human-authored texts remains unexplored. This study investigates how text generated by LLMs influences reading by analyzing gaze patterns. The study collects gaze data from 13 participants as they read AI- generated and human-authored passages. A comparative analysis is conducted within subjects to assess gaze patterns between authors and between text types based on the robust two-means clustering (I2MC) algorithm to identify fixations. In addition, pupil dilation and reading speed were examined. Our findings reveal significant differences in fixation character- istics not only between authors but also between AI-generated and human-authored texts.

AB - While Generative AI models like Large Language Models (LLMs) are capable of generating extensive text, their efficacy in producing readable content for human participants in experimental settings remains to be evaluated. Further, eye-tracking technology is increas- ingly utilized to study cognition and behavior, yet its application to readers’ cognitive processes when exposed to AI-generated versus human-authored texts remains unexplored. This study investigates how text generated by LLMs influences reading by analyzing gaze patterns. The study collects gaze data from 13 participants as they read AI- generated and human-authored passages. A comparative analysis is conducted within subjects to assess gaze patterns between authors and between text types based on the robust two-means clustering (I2MC) algorithm to identify fixations. In addition, pupil dilation and reading speed were examined. Our findings reveal significant differences in fixation character- istics not only between authors but also between AI-generated and human-authored texts.

KW - Eye-tracking

KW - Fixation detection

KW - AI and Human authored reading patterns

U2 - 10.1145/3715669.3726846

DO - 10.1145/3715669.3726846

M3 - Article in proceedings

SP - 1

EP - 7

BT - Proceedings of the 2025 Symposium on Eye Tracking Research and Applications (ETRA '25)

CY - Association for Computing Machinery

Y2 - 26 May 2025 through 29 May 2025

ER -