@inproceedings{pacheco-etal-2022-interactively,
title = "Interactively Uncovering Latent Arguments in Social Media Platforms: A Case Study on the Covid-19 Vaccine Debate",
author = "Pacheco, Maria Leonor and
Islam, Tunazzina and
Ungar, Lyle and
Yin, Ming and
Goldwasser, Dan",
editor = "Dragut, Eduard and
Li, Yunyao and
Popa, Lucian and
Vucetic, Slobodan and
Srivastava, Shashank",
booktitle = "Proceedings of the Fourth Workshop on Data Science with Human-in-the-Loop (Language Advances)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.dash-1.13",
pages = "94--111",
abstract = "Automated methods for analyzing public opinion have grown in popularity with the proliferation of social media. While supervised methods can be very good at classifying text, the dynamic nature of social media discourse results in a moving target for supervised learning. Meanwhile, traditional unsupervised techniques for extracting themes from textual repositories, such as topic models, can result in incorrect outputs that are unusable to domain experts. For this reason, a non-trivial amount of research on social media discourse still relies on manual coding techniques. In this paper, we present an interactive, humans-in-the-loop framework that strikes a balance between unsupervised techniques and manual coding for extracting latent arguments from social media discussions. We use the COVID-19 vaccination debate as a case study, and show that our methodology can be used to obtain a more accurate, interpretable set of arguments when compared to traditional topic models. We do this at a relatively low manual cost, as 3 experts take approximately 2 hours to code close to 100k tweets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pacheco-etal-2022-interactively">
<titleInfo>
<title>Interactively Uncovering Latent Arguments in Social Media Platforms: A Case Study on the Covid-19 Vaccine Debate</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Leonor</namePart>
<namePart type="family">Pacheco</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tunazzina</namePart>
<namePart type="family">Islam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lyle</namePart>
<namePart type="family">Ungar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ming</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Goldwasser</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>Proceedings of the Fourth Workshop on Data Science with Human-in-the-Loop (Language Advances)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eduard</namePart>
<namePart type="family">Dragut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucian</namePart>
<namePart type="family">Popa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Slobodan</namePart>
<namePart type="family">Vucetic</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shashank</namePart>
<namePart type="family">Srivastava</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 (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automated methods for analyzing public opinion have grown in popularity with the proliferation of social media. While supervised methods can be very good at classifying text, the dynamic nature of social media discourse results in a moving target for supervised learning. Meanwhile, traditional unsupervised techniques for extracting themes from textual repositories, such as topic models, can result in incorrect outputs that are unusable to domain experts. For this reason, a non-trivial amount of research on social media discourse still relies on manual coding techniques. In this paper, we present an interactive, humans-in-the-loop framework that strikes a balance between unsupervised techniques and manual coding for extracting latent arguments from social media discussions. We use the COVID-19 vaccination debate as a case study, and show that our methodology can be used to obtain a more accurate, interpretable set of arguments when compared to traditional topic models. We do this at a relatively low manual cost, as 3 experts take approximately 2 hours to code close to 100k tweets.</abstract>
<identifier type="citekey">pacheco-etal-2022-interactively</identifier>
<location>
<url>https://aclanthology.org/2022.dash-1.13</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>94</start>
<end>111</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Interactively Uncovering Latent Arguments in Social Media Platforms: A Case Study on the Covid-19 Vaccine Debate
%A Pacheco, Maria Leonor
%A Islam, Tunazzina
%A Ungar, Lyle
%A Yin, Ming
%A Goldwasser, Dan
%Y Dragut, Eduard
%Y Li, Yunyao
%Y Popa, Lucian
%Y Vucetic, Slobodan
%Y Srivastava, Shashank
%S Proceedings of the Fourth Workshop on Data Science with Human-in-the-Loop (Language Advances)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F pacheco-etal-2022-interactively
%X Automated methods for analyzing public opinion have grown in popularity with the proliferation of social media. While supervised methods can be very good at classifying text, the dynamic nature of social media discourse results in a moving target for supervised learning. Meanwhile, traditional unsupervised techniques for extracting themes from textual repositories, such as topic models, can result in incorrect outputs that are unusable to domain experts. For this reason, a non-trivial amount of research on social media discourse still relies on manual coding techniques. In this paper, we present an interactive, humans-in-the-loop framework that strikes a balance between unsupervised techniques and manual coding for extracting latent arguments from social media discussions. We use the COVID-19 vaccination debate as a case study, and show that our methodology can be used to obtain a more accurate, interpretable set of arguments when compared to traditional topic models. We do this at a relatively low manual cost, as 3 experts take approximately 2 hours to code close to 100k tweets.
%U https://aclanthology.org/2022.dash-1.13
%P 94-111
Markdown (Informal)
[Interactively Uncovering Latent Arguments in Social Media Platforms: A Case Study on the Covid-19 Vaccine Debate](https://aclanthology.org/2022.dash-1.13) (Pacheco et al., DaSH 2022)
ACL