@inproceedings{koo-etal-2024-platform,
title = "Platform-Invariant Topic Modeling via Contrastive Learning to Mitigate Platform-Induced Bias",
author = "Koo, Minseo and
Kim, Doeun and
Han, Sungwon and
Park, Sungkyu Shaun",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.650",
doi = "10.18653/v1/2024.findings-emnlp.650",
pages = "11123--11139",
abstract = "Cross-platform topic dissemination is one of the research subjects that delved into media analysis; sometimes it fails to grasp the authentic topics due to platform-induced biases, which may be caused by aggregating documents from multiple platforms and running them on an existing topic model. This work deals with the impact of unique platform characteristics on the performance of topic models and proposes a new approach to enhance the effectiveness of topic modeling. The data utilized in this study consisted of a total of 1.5 million posts collected using the keyword {''}ChatGPT{''} on the three social media platforms. The devised model reduces platform influence in topic models by developing a platform-invariant contrastive learning algorithm and removing platform-specific jargon word sets. The proposed approach was thoroughly validated through quantitative and qualitative experiments alongside standard and state-of-the-art topic models and showed its supremacy. This method can mitigate biases arising from platform influences when modeling topics from texts collected across various platforms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koo-etal-2024-platform">
<titleInfo>
<title>Platform-Invariant Topic Modeling via Contrastive Learning to Mitigate Platform-Induced Bias</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minseo</namePart>
<namePart type="family">Koo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Doeun</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sungwon</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sungkyu</namePart>
<namePart type="given">Shaun</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cross-platform topic dissemination is one of the research subjects that delved into media analysis; sometimes it fails to grasp the authentic topics due to platform-induced biases, which may be caused by aggregating documents from multiple platforms and running them on an existing topic model. This work deals with the impact of unique platform characteristics on the performance of topic models and proposes a new approach to enhance the effectiveness of topic modeling. The data utilized in this study consisted of a total of 1.5 million posts collected using the keyword ”ChatGPT” on the three social media platforms. The devised model reduces platform influence in topic models by developing a platform-invariant contrastive learning algorithm and removing platform-specific jargon word sets. The proposed approach was thoroughly validated through quantitative and qualitative experiments alongside standard and state-of-the-art topic models and showed its supremacy. This method can mitigate biases arising from platform influences when modeling topics from texts collected across various platforms.</abstract>
<identifier type="citekey">koo-etal-2024-platform</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.650</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.650</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>11123</start>
<end>11139</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Platform-Invariant Topic Modeling via Contrastive Learning to Mitigate Platform-Induced Bias
%A Koo, Minseo
%A Kim, Doeun
%A Han, Sungwon
%A Park, Sungkyu Shaun
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F koo-etal-2024-platform
%X Cross-platform topic dissemination is one of the research subjects that delved into media analysis; sometimes it fails to grasp the authentic topics due to platform-induced biases, which may be caused by aggregating documents from multiple platforms and running them on an existing topic model. This work deals with the impact of unique platform characteristics on the performance of topic models and proposes a new approach to enhance the effectiveness of topic modeling. The data utilized in this study consisted of a total of 1.5 million posts collected using the keyword ”ChatGPT” on the three social media platforms. The devised model reduces platform influence in topic models by developing a platform-invariant contrastive learning algorithm and removing platform-specific jargon word sets. The proposed approach was thoroughly validated through quantitative and qualitative experiments alongside standard and state-of-the-art topic models and showed its supremacy. This method can mitigate biases arising from platform influences when modeling topics from texts collected across various platforms.
%R 10.18653/v1/2024.findings-emnlp.650
%U https://aclanthology.org/2024.findings-emnlp.650
%U https://doi.org/10.18653/v1/2024.findings-emnlp.650
%P 11123-11139
Markdown (Informal)
[Platform-Invariant Topic Modeling via Contrastive Learning to Mitigate Platform-Induced Bias](https://aclanthology.org/2024.findings-emnlp.650) (Koo et al., Findings 2024)
ACL