@inproceedings{bohacek-2022-misinformation,
title = "Misinformation Detection in the Wild: News Source Classification as a Proxy for Non-article Texts",
author = "Bohacek, Matyas",
editor = "Biester, Laura and
Demszky, Dorottya and
Jin, Zhijing and
Sachan, Mrinmaya and
Tetreault, Joel and
Wilson, Steven and
Xiao, Lu and
Zhao, Jieyu",
booktitle = "Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI)",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.nlp4pi-1.10",
doi = "10.18653/v1/2022.nlp4pi-1.10",
pages = "79--88",
abstract = "Creating classifiers of disinformation is time-consuming, expensive, and requires vast effort from experts spanning different fields. Even when these efforts succeed, their roll-out to publicly available applications stagnates. While these models struggle to find their consumer-accessible use, disinformation behavior online evolves at a pressing speed. The hoaxes get shared in various abbreviations on social networks, often in user-restricted areas, making external monitoring and intervention virtually impossible. To re-purpose existing NLP methods for the new paradigm of sharing misinformation, we propose leveraging information about given texts{'} originating news sources to proxy the respective text{'}s trustworthiness. We first present a methodology for determining the sources{'} overall credibility. We demonstrate our pipeline construction in a specific language and introduce CNSC: a novel dataset for Czech articles{'} news source and source credibility classification. We constitute initial benchmarks on multiple architectures. Lastly, we create in-the-wild wrapper applications of the trained models: a chatbot, a browser extension, and a standalone web application.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bohacek-2022-misinformation">
<titleInfo>
<title>Misinformation Detection in the Wild: News Source Classification as a Proxy for Non-article Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matyas</namePart>
<namePart type="family">Bohacek</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 Second Workshop on NLP for Positive Impact (NLP4PI)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Biester</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dorottya</namePart>
<namePart type="family">Demszky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhijing</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mrinmaya</namePart>
<namePart type="family">Sachan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Wilson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieyu</namePart>
<namePart type="family">Zhao</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>Creating classifiers of disinformation is time-consuming, expensive, and requires vast effort from experts spanning different fields. Even when these efforts succeed, their roll-out to publicly available applications stagnates. While these models struggle to find their consumer-accessible use, disinformation behavior online evolves at a pressing speed. The hoaxes get shared in various abbreviations on social networks, often in user-restricted areas, making external monitoring and intervention virtually impossible. To re-purpose existing NLP methods for the new paradigm of sharing misinformation, we propose leveraging information about given texts’ originating news sources to proxy the respective text’s trustworthiness. We first present a methodology for determining the sources’ overall credibility. We demonstrate our pipeline construction in a specific language and introduce CNSC: a novel dataset for Czech articles’ news source and source credibility classification. We constitute initial benchmarks on multiple architectures. Lastly, we create in-the-wild wrapper applications of the trained models: a chatbot, a browser extension, and a standalone web application.</abstract>
<identifier type="citekey">bohacek-2022-misinformation</identifier>
<identifier type="doi">10.18653/v1/2022.nlp4pi-1.10</identifier>
<location>
<url>https://aclanthology.org/2022.nlp4pi-1.10</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>79</start>
<end>88</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Misinformation Detection in the Wild: News Source Classification as a Proxy for Non-article Texts
%A Bohacek, Matyas
%Y Biester, Laura
%Y Demszky, Dorottya
%Y Jin, Zhijing
%Y Sachan, Mrinmaya
%Y Tetreault, Joel
%Y Wilson, Steven
%Y Xiao, Lu
%Y Zhao, Jieyu
%S Proceedings of the Second Workshop on NLP for Positive Impact (NLP4PI)
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F bohacek-2022-misinformation
%X Creating classifiers of disinformation is time-consuming, expensive, and requires vast effort from experts spanning different fields. Even when these efforts succeed, their roll-out to publicly available applications stagnates. While these models struggle to find their consumer-accessible use, disinformation behavior online evolves at a pressing speed. The hoaxes get shared in various abbreviations on social networks, often in user-restricted areas, making external monitoring and intervention virtually impossible. To re-purpose existing NLP methods for the new paradigm of sharing misinformation, we propose leveraging information about given texts’ originating news sources to proxy the respective text’s trustworthiness. We first present a methodology for determining the sources’ overall credibility. We demonstrate our pipeline construction in a specific language and introduce CNSC: a novel dataset for Czech articles’ news source and source credibility classification. We constitute initial benchmarks on multiple architectures. Lastly, we create in-the-wild wrapper applications of the trained models: a chatbot, a browser extension, and a standalone web application.
%R 10.18653/v1/2022.nlp4pi-1.10
%U https://aclanthology.org/2022.nlp4pi-1.10
%U https://doi.org/10.18653/v1/2022.nlp4pi-1.10
%P 79-88
Markdown (Informal)
[Misinformation Detection in the Wild: News Source Classification as a Proxy for Non-article Texts](https://aclanthology.org/2022.nlp4pi-1.10) (Bohacek, NLP4PI 2022)
ACL