@inproceedings{acarturk-etal-2026-survey,
title = "A Survey of Incorporating Gaze Data into Natural Language Processing Models and Applications",
author = "Acarturk, Cengiz and
Can, Burcu and
Caglayan, Melike and
Abdul Nasir, Jamal and
Coltekin, Cagri",
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-1.10/",
doi = "10.63317/24jihahajx5n",
pages = "64--76",
abstract = "This study presents a survey of research integrating eye-tracking (gaze) data into Language Models (LMs) as a means of cognitively grounding NLP models and applications in human reading behavior. Although contemporary LMs excel at learning statistical patterns from text, they fundamentally lack human-like reading and comprehension capabilities. Incorporating gaze data may offer a window into cognitive processing, yet its impact on LMs remains underexplored. Addressing a persistent bottleneck, namely, the high cost and limited scale of laboratory eye-tracking, we propose a roadmap consisting of three streams of research for advancing this novel research domain: (1) developing cognitive multimodal corpora, (2) leveraging generative models for gaze synthesis to overcome the data bottleneck caused by the high costs of human eye-tracking, and (3) training LMs with gaze-guided attention mechanisms and input augmentation. Furthermore, we illustrate practical applications in readability assessment, educational analytics, and assistive communication, demonstrating how gaze-informed models can enable adaptive technologies. Finally, we critically examine ongoing challenges, including the lack of data standardization, the misalignment between human and machine language processing, and the urgent ethical imperative for privacy-preserving architectures to protect sensitive biometric gaze data, motivating privacy-aware data practices and model designs for scalable deployment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="acarturk-etal-2026-survey">
<titleInfo>
<title>A Survey of Incorporating Gaze Data into Natural Language Processing Models and Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Cengiz</namePart>
<namePart type="family">Acarturk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Burcu</namePart>
<namePart type="family">Can</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Melike</namePart>
<namePart type="family">Caglayan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jamal</namePart>
<namePart type="family">Abdul Nasir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cagri</namePart>
<namePart type="family">Coltekin</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>This study presents a survey of research integrating eye-tracking (gaze) data into Language Models (LMs) as a means of cognitively grounding NLP models and applications in human reading behavior. Although contemporary LMs excel at learning statistical patterns from text, they fundamentally lack human-like reading and comprehension capabilities. Incorporating gaze data may offer a window into cognitive processing, yet its impact on LMs remains underexplored. Addressing a persistent bottleneck, namely, the high cost and limited scale of laboratory eye-tracking, we propose a roadmap consisting of three streams of research for advancing this novel research domain: (1) developing cognitive multimodal corpora, (2) leveraging generative models for gaze synthesis to overcome the data bottleneck caused by the high costs of human eye-tracking, and (3) training LMs with gaze-guided attention mechanisms and input augmentation. Furthermore, we illustrate practical applications in readability assessment, educational analytics, and assistive communication, demonstrating how gaze-informed models can enable adaptive technologies. Finally, we critically examine ongoing challenges, including the lack of data standardization, the misalignment between human and machine language processing, and the urgent ethical imperative for privacy-preserving architectures to protect sensitive biometric gaze data, motivating privacy-aware data practices and model designs for scalable deployment.</abstract>
<identifier type="citekey">acarturk-etal-2026-survey</identifier>
<identifier type="doi">10.63317/24jihahajx5n</identifier>
<location>
<url>https://aclanthology.org/2026.gaze4nlp-1.10/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>64</start>
<end>76</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Survey of Incorporating Gaze Data into Natural Language Processing Models and Applications
%A Acarturk, Cengiz
%A Can, Burcu
%A Caglayan, Melike
%A Abdul Nasir, Jamal
%A Coltekin, Cagri
%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 acarturk-etal-2026-survey
%X This study presents a survey of research integrating eye-tracking (gaze) data into Language Models (LMs) as a means of cognitively grounding NLP models and applications in human reading behavior. Although contemporary LMs excel at learning statistical patterns from text, they fundamentally lack human-like reading and comprehension capabilities. Incorporating gaze data may offer a window into cognitive processing, yet its impact on LMs remains underexplored. Addressing a persistent bottleneck, namely, the high cost and limited scale of laboratory eye-tracking, we propose a roadmap consisting of three streams of research for advancing this novel research domain: (1) developing cognitive multimodal corpora, (2) leveraging generative models for gaze synthesis to overcome the data bottleneck caused by the high costs of human eye-tracking, and (3) training LMs with gaze-guided attention mechanisms and input augmentation. Furthermore, we illustrate practical applications in readability assessment, educational analytics, and assistive communication, demonstrating how gaze-informed models can enable adaptive technologies. Finally, we critically examine ongoing challenges, including the lack of data standardization, the misalignment between human and machine language processing, and the urgent ethical imperative for privacy-preserving architectures to protect sensitive biometric gaze data, motivating privacy-aware data practices and model designs for scalable deployment.
%R 10.63317/24jihahajx5n
%U https://aclanthology.org/2026.gaze4nlp-1.10/
%U https://doi.org/10.63317/24jihahajx5n
%P 64-76
Markdown (Informal)
[A Survey of Incorporating Gaze Data into Natural Language Processing Models and Applications](https://aclanthology.org/2026.gaze4nlp-1.10/) (Acarturk et al., Gaze4NLP 2026)
ACL