@inproceedings{baazeem-etal-2026-cross,
title = "Cross-Linguistic Analysis of Eye Movement Patterns: Insights from the First {A}rabic Eye-Tracking Corpus for {NLP}",
author = "Baazeem, Ibtehal and
Al-Khalifa, Hend and
AlSalman, Abdulmalik",
editor = {Acart{\"u}rk, Cengiz and
Can, Burcu and
Nasir, Jamal and
{\c{C}}{\"o}ltekin, {\c{C}}a{\u{g}}r{\i}},
booktitle = "Proceedings fo the Second International Workshop on Eye-Tracking Resources and Evaluation for Human-Aligned {NLP}",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELDA",
url = "https://aclanthology.org/2026.gaze4nlp-1.2/",
doi = "10.63317/4t25sphn6p46",
pages = "10--15",
abstract = "Eye-tracking corpora have become valuable resources for understanding human reading behavior and developing cognitively-informed NLP models. However, existing resources predominantly focus on left-to-right Latin script languages, leaving a significant gap for morphologically rich, right-to-left languages like Arabic. This paper presents a cross-linguistic analysis of eye movement patterns using the AraEyebility corpus, the first Arabic eye-tracking corpus comprising 57,617 words read by 15 native speakers. We systematically compare gaze metrics across Arabic and established English corpora. Our analysis reveals distinct patterns in fixation duration, saccade length, and regression frequency that reflect Arabic{'}s unique orthographic properties: cursive script, diacritization, bidirectional reading (text right-to-left, numbers left-to-right), and morphological complexity. The findings demonstrate that Arabic readers exhibit longer mean fixation durations and more frequent regressions compared to English readers, suggesting higher cognitive processing demands. We discuss implications for developing cognitively-aligned NLP models and provide recommendations for future multilingual eye-tracking research. The AraEyebility corpus is publicly available to support Arabic NLP research."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="baazeem-etal-2026-cross">
<titleInfo>
<title>Cross-Linguistic Analysis of Eye Movement Patterns: Insights from the First Arabic Eye-Tracking Corpus for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ibtehal</namePart>
<namePart type="family">Baazeem</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdulmalik</namePart>
<namePart type="family">AlSalman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings fo the Second International Workshop on Eye-Tracking Resources and Evaluation for Human-Aligned NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cengiz</namePart>
<namePart type="family">Acartürk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Burcu</namePart>
<namePart type="family">Can</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jamal</namePart>
<namePart type="family">Nasir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Çağrı</namePart>
<namePart type="family">Çöltekin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELDA</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Eye-tracking corpora have become valuable resources for understanding human reading behavior and developing cognitively-informed NLP models. However, existing resources predominantly focus on left-to-right Latin script languages, leaving a significant gap for morphologically rich, right-to-left languages like Arabic. This paper presents a cross-linguistic analysis of eye movement patterns using the AraEyebility corpus, the first Arabic eye-tracking corpus comprising 57,617 words read by 15 native speakers. We systematically compare gaze metrics across Arabic and established English corpora. Our analysis reveals distinct patterns in fixation duration, saccade length, and regression frequency that reflect Arabic’s unique orthographic properties: cursive script, diacritization, bidirectional reading (text right-to-left, numbers left-to-right), and morphological complexity. The findings demonstrate that Arabic readers exhibit longer mean fixation durations and more frequent regressions compared to English readers, suggesting higher cognitive processing demands. We discuss implications for developing cognitively-aligned NLP models and provide recommendations for future multilingual eye-tracking research. The AraEyebility corpus is publicly available to support Arabic NLP research.</abstract>
<identifier type="citekey">baazeem-etal-2026-cross</identifier>
<identifier type="doi">10.63317/4t25sphn6p46</identifier>
<location>
<url>https://aclanthology.org/2026.gaze4nlp-1.2/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>10</start>
<end>15</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Linguistic Analysis of Eye Movement Patterns: Insights from the First Arabic Eye-Tracking Corpus for NLP
%A Baazeem, Ibtehal
%A Al-Khalifa, Hend
%A AlSalman, Abdulmalik
%Y Acartürk, Cengiz
%Y Can, Burcu
%Y Nasir, Jamal
%Y Çöltekin, Çağrı
%S Proceedings fo the Second International Workshop on Eye-Tracking Resources and Evaluation for Human-Aligned NLP
%D 2026
%8 May
%I ELDA
%C Palma de Mallorca, Spain
%F baazeem-etal-2026-cross
%X Eye-tracking corpora have become valuable resources for understanding human reading behavior and developing cognitively-informed NLP models. However, existing resources predominantly focus on left-to-right Latin script languages, leaving a significant gap for morphologically rich, right-to-left languages like Arabic. This paper presents a cross-linguistic analysis of eye movement patterns using the AraEyebility corpus, the first Arabic eye-tracking corpus comprising 57,617 words read by 15 native speakers. We systematically compare gaze metrics across Arabic and established English corpora. Our analysis reveals distinct patterns in fixation duration, saccade length, and regression frequency that reflect Arabic’s unique orthographic properties: cursive script, diacritization, bidirectional reading (text right-to-left, numbers left-to-right), and morphological complexity. The findings demonstrate that Arabic readers exhibit longer mean fixation durations and more frequent regressions compared to English readers, suggesting higher cognitive processing demands. We discuss implications for developing cognitively-aligned NLP models and provide recommendations for future multilingual eye-tracking research. The AraEyebility corpus is publicly available to support Arabic NLP research.
%R 10.63317/4t25sphn6p46
%U https://aclanthology.org/2026.gaze4nlp-1.2/
%U https://doi.org/10.63317/4t25sphn6p46
%P 10-15
Markdown (Informal)
[Cross-Linguistic Analysis of Eye Movement Patterns: Insights from the First Arabic Eye-Tracking Corpus for NLP](https://aclanthology.org/2026.gaze4nlp-1.2/) (Baazeem et al., Gaze4NLP 2026)
ACL