@inproceedings{soni-etal-2022-predicting,
title = "Predicting Long-Term Citations from Short-Term Linguistic Influence",
author = "Soni, Sandeep and
Bamman, David and
Eisenstein, Jacob",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.418",
doi = "10.18653/v1/2022.findings-emnlp.418",
pages = "5700--5716",
abstract = "A standard measure of the influence of a research paper is the number of times it is cited. However, papers may be cited for many reasons, and citation count is not informative about the extent to which a paper affected the content of subsequent publications. We therefore propose a novel method to quantify linguistic influence in timestamped document collections. There are two main steps: first, identify lexical and semantic changes using contextual embeddings and word frequencies; second, aggregate information about these changes into per-document influence parameters by estimating a high-dimensional Hawkes process with a low-rank parameter matrix. The resulting measures of linguistic influence are predictive of \textit{future} citations. Specifically, the estimate of linguistic influence from the two years after a paper{'}s publication is correlated with and predictive of its citation count in the following three years. This is demonstrated using an online evaluation with incremental temporal training/test splits, in comparison with a strong baseline that includes predictors for initial citation counts, topics, and lexical features.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="soni-etal-2022-predicting">
<titleInfo>
<title>Predicting Long-Term Citations from Short-Term Linguistic Influence</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sandeep</namePart>
<namePart type="family">Soni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Bamman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="family">Eisenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A standard measure of the influence of a research paper is the number of times it is cited. However, papers may be cited for many reasons, and citation count is not informative about the extent to which a paper affected the content of subsequent publications. We therefore propose a novel method to quantify linguistic influence in timestamped document collections. There are two main steps: first, identify lexical and semantic changes using contextual embeddings and word frequencies; second, aggregate information about these changes into per-document influence parameters by estimating a high-dimensional Hawkes process with a low-rank parameter matrix. The resulting measures of linguistic influence are predictive of future citations. Specifically, the estimate of linguistic influence from the two years after a paper’s publication is correlated with and predictive of its citation count in the following three years. This is demonstrated using an online evaluation with incremental temporal training/test splits, in comparison with a strong baseline that includes predictors for initial citation counts, topics, and lexical features.</abstract>
<identifier type="citekey">soni-etal-2022-predicting</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.418</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.418</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>5700</start>
<end>5716</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Predicting Long-Term Citations from Short-Term Linguistic Influence
%A Soni, Sandeep
%A Bamman, David
%A Eisenstein, Jacob
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F soni-etal-2022-predicting
%X A standard measure of the influence of a research paper is the number of times it is cited. However, papers may be cited for many reasons, and citation count is not informative about the extent to which a paper affected the content of subsequent publications. We therefore propose a novel method to quantify linguistic influence in timestamped document collections. There are two main steps: first, identify lexical and semantic changes using contextual embeddings and word frequencies; second, aggregate information about these changes into per-document influence parameters by estimating a high-dimensional Hawkes process with a low-rank parameter matrix. The resulting measures of linguistic influence are predictive of future citations. Specifically, the estimate of linguistic influence from the two years after a paper’s publication is correlated with and predictive of its citation count in the following three years. This is demonstrated using an online evaluation with incremental temporal training/test splits, in comparison with a strong baseline that includes predictors for initial citation counts, topics, and lexical features.
%R 10.18653/v1/2022.findings-emnlp.418
%U https://aclanthology.org/2022.findings-emnlp.418
%U https://doi.org/10.18653/v1/2022.findings-emnlp.418
%P 5700-5716
Markdown (Informal)
[Predicting Long-Term Citations from Short-Term Linguistic Influence](https://aclanthology.org/2022.findings-emnlp.418) (Soni et al., Findings 2022)
ACL