@inproceedings{hopp-etal-2025-persistent,
title = "Persistent Homology of Topic Networks for the Prediction of Reader Curiosity",
author = "Hopp, Manuel D. S. and
Labatut, Vincent and
Amalvy, Arthur and
Dufour, Richard and
Stone, Hannah and
Jach, Hayley and
Murayama, Kou",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.1364/",
doi = "10.18653/v1/2025.acl-long.1364",
pages = "28121--28132",
ISBN = "979-8-89176-251-0",
abstract = "Reader curiosity, the drive to seek information, is crucial for textual engagement, yet remains relatively underexplored in NLP. Building on Loewenstein{'}s Information Gap Theory, we introduce a framework that models reader curiosity by quantifying semantic information gaps within a text{'}s semantic structure. Our approach leverages BERTopic-inspired topic modeling and persistent homology to analyze the evolving topology (connected components, cycles, voids) of a dynamic semantic network derived from text segments, treating these features as proxies for information gaps. To empirically evaluate this pipeline, we collect reader curiosity ratings from participants ($n = 49$) as they read S. Collins{'}s ``The Hunger Games'' novel. We then use the topological features from our pipeline as independent variables to predict these ratings, and experimentally show that they significantly improve curiosity prediction compared to a baseline model (73{\%} vs. 30{\%} explained deviance), validating our approach. This pipeline offers a new computational method for analyzing text structure and its relation to reader engagement."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hopp-etal-2025-persistent">
<titleInfo>
<title>Persistent Homology of Topic Networks for the Prediction of Reader Curiosity</title>
</titleInfo>
<name type="personal">
<namePart type="given">Manuel</namePart>
<namePart type="given">D</namePart>
<namePart type="given">S</namePart>
<namePart type="family">Hopp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Labatut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arthur</namePart>
<namePart type="family">Amalvy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Dufour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannah</namePart>
<namePart type="family">Stone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hayley</namePart>
<namePart type="family">Jach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kou</namePart>
<namePart type="family">Murayama</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>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>Reader curiosity, the drive to seek information, is crucial for textual engagement, yet remains relatively underexplored in NLP. Building on Loewenstein’s Information Gap Theory, we introduce a framework that models reader curiosity by quantifying semantic information gaps within a text’s semantic structure. Our approach leverages BERTopic-inspired topic modeling and persistent homology to analyze the evolving topology (connected components, cycles, voids) of a dynamic semantic network derived from text segments, treating these features as proxies for information gaps. To empirically evaluate this pipeline, we collect reader curiosity ratings from participants (n = 49) as they read S. Collins’s “The Hunger Games” novel. We then use the topological features from our pipeline as independent variables to predict these ratings, and experimentally show that they significantly improve curiosity prediction compared to a baseline model (73% vs. 30% explained deviance), validating our approach. This pipeline offers a new computational method for analyzing text structure and its relation to reader engagement.</abstract>
<identifier type="citekey">hopp-etal-2025-persistent</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.1364</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.1364/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>28121</start>
<end>28132</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Persistent Homology of Topic Networks for the Prediction of Reader Curiosity
%A Hopp, Manuel D. S.
%A Labatut, Vincent
%A Amalvy, Arthur
%A Dufour, Richard
%A Stone, Hannah
%A Jach, Hayley
%A Murayama, Kou
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F hopp-etal-2025-persistent
%X Reader curiosity, the drive to seek information, is crucial for textual engagement, yet remains relatively underexplored in NLP. Building on Loewenstein’s Information Gap Theory, we introduce a framework that models reader curiosity by quantifying semantic information gaps within a text’s semantic structure. Our approach leverages BERTopic-inspired topic modeling and persistent homology to analyze the evolving topology (connected components, cycles, voids) of a dynamic semantic network derived from text segments, treating these features as proxies for information gaps. To empirically evaluate this pipeline, we collect reader curiosity ratings from participants (n = 49) as they read S. Collins’s “The Hunger Games” novel. We then use the topological features from our pipeline as independent variables to predict these ratings, and experimentally show that they significantly improve curiosity prediction compared to a baseline model (73% vs. 30% explained deviance), validating our approach. This pipeline offers a new computational method for analyzing text structure and its relation to reader engagement.
%R 10.18653/v1/2025.acl-long.1364
%U https://aclanthology.org/2025.acl-long.1364/
%U https://doi.org/10.18653/v1/2025.acl-long.1364
%P 28121-28132
Markdown (Informal)
[Persistent Homology of Topic Networks for the Prediction of Reader Curiosity](https://aclanthology.org/2025.acl-long.1364/) (Hopp et al., ACL 2025)
ACL
- Manuel D. S. Hopp, Vincent Labatut, Arthur Amalvy, Richard Dufour, Hannah Stone, Hayley Jach, and Kou Murayama. 2025. Persistent Homology of Topic Networks for the Prediction of Reader Curiosity. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 28121–28132, Vienna, Austria. Association for Computational Linguistics.