@inproceedings{bittermann-rieger-2022-finding,
title = "Finding Scientific Topics in Continuously Growing Text Corpora",
author = "Bittermann, Andr{\'e} and
Rieger, Jonas",
editor = "Cohan, Arman and
Feigenblat, Guy and
Freitag, Dayne and
Ghosal, Tirthankar and
Herrmannova, Drahomira and
Knoth, Petr and
Lo, Kyle and
Mayr, Philipp and
Shmueli-Scheuer, Michal and
de Waard, Anita and
Wang, Lucy Lu",
booktitle = "Proceedings of the Third Workshop on Scholarly Document Processing",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.sdp-1.2",
pages = "7--18",
abstract = "The ever growing amount of research publications demands computational assistance for everyone trying to keep track with scientific processes. Topic modeling has become a popular approach for finding scientific topics in static collections of research papers. However, the reality of continuously growing corpora of scholarly documents poses a major challenge for traditional approaches. We introduce RollingLDA for an ongoing monitoring of research topics, which offers the possibility of sequential modeling of dynamically growing corpora with time consistency of time series resulting from the modeled texts. We evaluate its capability to detect research topics and present a Shiny App as an easy-to-use interface. In addition, we illustrate usage scenarios for different user groups such as researchers, students, journalists, or policy-makers.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bittermann-rieger-2022-finding">
<titleInfo>
<title>Finding Scientific Topics in Continuously Growing Text Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Bittermann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonas</namePart>
<namePart type="family">Rieger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Scholarly Document Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arman</namePart>
<namePart type="family">Cohan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Feigenblat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dayne</namePart>
<namePart type="family">Freitag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Ghosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Drahomira</namePart>
<namePart type="family">Herrmannova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petr</namePart>
<namePart type="family">Knoth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Mayr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Shmueli-Scheuer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">de Waard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucy</namePart>
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The ever growing amount of research publications demands computational assistance for everyone trying to keep track with scientific processes. Topic modeling has become a popular approach for finding scientific topics in static collections of research papers. However, the reality of continuously growing corpora of scholarly documents poses a major challenge for traditional approaches. We introduce RollingLDA for an ongoing monitoring of research topics, which offers the possibility of sequential modeling of dynamically growing corpora with time consistency of time series resulting from the modeled texts. We evaluate its capability to detect research topics and present a Shiny App as an easy-to-use interface. In addition, we illustrate usage scenarios for different user groups such as researchers, students, journalists, or policy-makers.</abstract>
<identifier type="citekey">bittermann-rieger-2022-finding</identifier>
<location>
<url>https://aclanthology.org/2022.sdp-1.2</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>7</start>
<end>18</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Finding Scientific Topics in Continuously Growing Text Corpora
%A Bittermann, André
%A Rieger, Jonas
%Y Cohan, Arman
%Y Feigenblat, Guy
%Y Freitag, Dayne
%Y Ghosal, Tirthankar
%Y Herrmannova, Drahomira
%Y Knoth, Petr
%Y Lo, Kyle
%Y Mayr, Philipp
%Y Shmueli-Scheuer, Michal
%Y de Waard, Anita
%Y Wang, Lucy Lu
%S Proceedings of the Third Workshop on Scholarly Document Processing
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F bittermann-rieger-2022-finding
%X The ever growing amount of research publications demands computational assistance for everyone trying to keep track with scientific processes. Topic modeling has become a popular approach for finding scientific topics in static collections of research papers. However, the reality of continuously growing corpora of scholarly documents poses a major challenge for traditional approaches. We introduce RollingLDA for an ongoing monitoring of research topics, which offers the possibility of sequential modeling of dynamically growing corpora with time consistency of time series resulting from the modeled texts. We evaluate its capability to detect research topics and present a Shiny App as an easy-to-use interface. In addition, we illustrate usage scenarios for different user groups such as researchers, students, journalists, or policy-makers.
%U https://aclanthology.org/2022.sdp-1.2
%P 7-18
Markdown (Informal)
[Finding Scientific Topics in Continuously Growing Text Corpora](https://aclanthology.org/2022.sdp-1.2) (Bittermann & Rieger, sdp 2022)
ACL