@inproceedings{scelsi-etal-2021-principled,
title = "Principled Analysis of Energy Discourse across Domains with Thesaurus-based Automatic Topic Labeling",
author = "Scelsi, Thomas and
Arranz, Alfonso Martinez and
Frermann, Lea",
editor = "Rahimi, Afshin and
Lane, William and
Zuccon, Guido",
booktitle = "Proceedings of the 19th Annual Workshop of the Australasian Language Technology Association",
month = dec,
year = "2021",
address = "Online",
publisher = "Australasian Language Technology Association",
url = "https://aclanthology.org/2021.alta-1.11",
pages = "107--118",
abstract = "With the increasing impact of Natural Language Processing tools like topic models in social science research, the experimental rigor and comparability of models and datasets has come under scrutiny. Especially when contributing to research on topics with worldwide impacts like energy policy, objective analyses and reliable datasets are necessary. We contribute toward this goal in two ways: first, we release two diachronic corpora covering 23 years of energy discussions in the U.S. Energy Information Administration. Secondly, we propose a simple and theoretically sound method for automatic topic labelling drawing on political thesauri. We empirically evaluate the quality of our labels, and apply our labelling to topics induced by diachronic topic models on our energy corpora, and present a detailed analysis.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scelsi-etal-2021-principled">
<titleInfo>
<title>Principled Analysis of Energy Discourse across Domains with Thesaurus-based Automatic Topic Labeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Scelsi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alfonso</namePart>
<namePart type="given">Martinez</namePart>
<namePart type="family">Arranz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lea</namePart>
<namePart type="family">Frermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Annual Workshop of the Australasian Language Technology Association</title>
</titleInfo>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Lane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guido</namePart>
<namePart type="family">Zuccon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Australasian Language Technology Association</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the increasing impact of Natural Language Processing tools like topic models in social science research, the experimental rigor and comparability of models and datasets has come under scrutiny. Especially when contributing to research on topics with worldwide impacts like energy policy, objective analyses and reliable datasets are necessary. We contribute toward this goal in two ways: first, we release two diachronic corpora covering 23 years of energy discussions in the U.S. Energy Information Administration. Secondly, we propose a simple and theoretically sound method for automatic topic labelling drawing on political thesauri. We empirically evaluate the quality of our labels, and apply our labelling to topics induced by diachronic topic models on our energy corpora, and present a detailed analysis.</abstract>
<identifier type="citekey">scelsi-etal-2021-principled</identifier>
<location>
<url>https://aclanthology.org/2021.alta-1.11</url>
</location>
<part>
<date>2021-12</date>
<extent unit="page">
<start>107</start>
<end>118</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Principled Analysis of Energy Discourse across Domains with Thesaurus-based Automatic Topic Labeling
%A Scelsi, Thomas
%A Arranz, Alfonso Martinez
%A Frermann, Lea
%Y Rahimi, Afshin
%Y Lane, William
%Y Zuccon, Guido
%S Proceedings of the 19th Annual Workshop of the Australasian Language Technology Association
%D 2021
%8 December
%I Australasian Language Technology Association
%C Online
%F scelsi-etal-2021-principled
%X With the increasing impact of Natural Language Processing tools like topic models in social science research, the experimental rigor and comparability of models and datasets has come under scrutiny. Especially when contributing to research on topics with worldwide impacts like energy policy, objective analyses and reliable datasets are necessary. We contribute toward this goal in two ways: first, we release two diachronic corpora covering 23 years of energy discussions in the U.S. Energy Information Administration. Secondly, we propose a simple and theoretically sound method for automatic topic labelling drawing on political thesauri. We empirically evaluate the quality of our labels, and apply our labelling to topics induced by diachronic topic models on our energy corpora, and present a detailed analysis.
%U https://aclanthology.org/2021.alta-1.11
%P 107-118
Markdown (Informal)
[Principled Analysis of Energy Discourse across Domains with Thesaurus-based Automatic Topic Labeling](https://aclanthology.org/2021.alta-1.11) (Scelsi et al., ALTA 2021)
ACL