@inproceedings{scozzaro-etal-2025-beyond,
title = "Beyond the Average Reader: the Reader Embedding Approach",
author = "Scozzaro, Calogero Jerik and
Delsanto, Matteo and
Radicioni, Daniele P.",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.789/",
doi = "10.18653/v1/2025.findings-acl.789",
pages = "15231--15244",
ISBN = "979-8-89176-256-5",
abstract = "Focus of this work is the prediction of reading times as the task is customarily dealt with in literature: that is, by collecting eye-tracking data that are averaged and employed to train learning models. We start by observing that systems trained on average values are ill-suited for the prediction of the reading times for specific subjects, as they fail to account for individual variability and accurately analyze the reading gestures of specific reader groups, or to target specific user needs. To overcome such limitation, that is to predict the reading times for a specific subject, we propose a novel approach based on creating an embedding to compactly describe her/his fixations. Embeddings are used to individuate readers that share same or similar reading behavior from a reference corpus. Models are then trained on values averaged over this subset of similar readers. Experimental results indicate that the proposed approach consistently outperforms its corresponding variants, in which predictions of reading times for specific readers are based on data from all subjects rather than from the most similar ones."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scozzaro-etal-2025-beyond">
<titleInfo>
<title>Beyond the Average Reader: the Reader Embedding Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Calogero</namePart>
<namePart type="given">Jerik</namePart>
<namePart type="family">Scozzaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Delsanto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniele</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Radicioni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Focus of this work is the prediction of reading times as the task is customarily dealt with in literature: that is, by collecting eye-tracking data that are averaged and employed to train learning models. We start by observing that systems trained on average values are ill-suited for the prediction of the reading times for specific subjects, as they fail to account for individual variability and accurately analyze the reading gestures of specific reader groups, or to target specific user needs. To overcome such limitation, that is to predict the reading times for a specific subject, we propose a novel approach based on creating an embedding to compactly describe her/his fixations. Embeddings are used to individuate readers that share same or similar reading behavior from a reference corpus. Models are then trained on values averaged over this subset of similar readers. Experimental results indicate that the proposed approach consistently outperforms its corresponding variants, in which predictions of reading times for specific readers are based on data from all subjects rather than from the most similar ones.</abstract>
<identifier type="citekey">scozzaro-etal-2025-beyond</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.789</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.789/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>15231</start>
<end>15244</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond the Average Reader: the Reader Embedding Approach
%A Scozzaro, Calogero Jerik
%A Delsanto, Matteo
%A Radicioni, Daniele P.
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F scozzaro-etal-2025-beyond
%X Focus of this work is the prediction of reading times as the task is customarily dealt with in literature: that is, by collecting eye-tracking data that are averaged and employed to train learning models. We start by observing that systems trained on average values are ill-suited for the prediction of the reading times for specific subjects, as they fail to account for individual variability and accurately analyze the reading gestures of specific reader groups, or to target specific user needs. To overcome such limitation, that is to predict the reading times for a specific subject, we propose a novel approach based on creating an embedding to compactly describe her/his fixations. Embeddings are used to individuate readers that share same or similar reading behavior from a reference corpus. Models are then trained on values averaged over this subset of similar readers. Experimental results indicate that the proposed approach consistently outperforms its corresponding variants, in which predictions of reading times for specific readers are based on data from all subjects rather than from the most similar ones.
%R 10.18653/v1/2025.findings-acl.789
%U https://aclanthology.org/2025.findings-acl.789/
%U https://doi.org/10.18653/v1/2025.findings-acl.789
%P 15231-15244
Markdown (Informal)
[Beyond the Average Reader: the Reader Embedding Approach](https://aclanthology.org/2025.findings-acl.789/) (Scozzaro et al., Findings 2025)
ACL
- Calogero Jerik Scozzaro, Matteo Delsanto, and Daniele P. Radicioni. 2025. Beyond the Average Reader: the Reader Embedding Approach. In Findings of the Association for Computational Linguistics: ACL 2025, pages 15231–15244, Vienna, Austria. Association for Computational Linguistics.