@inproceedings{volkova-etal-2017-separating,
title = "Separating Facts from Fiction: Linguistic Models to Classify Suspicious and Trusted News Posts on {T}witter",
author = "Volkova, Svitlana and
Shaffer, Kyle and
Jang, Jin Yea and
Hodas, Nathan",
editor = "Barzilay, Regina and
Kan, Min-Yen",
booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
month = jul,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P17-2102",
doi = "10.18653/v1/P17-2102",
pages = "647--653",
abstract = "Pew research polls report 62 percent of U.S. adults get news on social media (Gottfried and Shearer, 2016). In a December poll, 64 percent of U.S. adults said that {``}made-up news{''} has caused a {``}great deal of confusion{''} about the facts of current events (Barthel et al., 2016). Fabricated stories in social media, ranging from deliberate propaganda to hoaxes and satire, contributes to this confusion in addition to having serious effects on global stability. In this work we build predictive models to classify 130 thousand news posts as suspicious or verified, and predict four sub-types of suspicious news {--} satire, hoaxes, clickbait and propaganda. We show that neural network models trained on tweet content and social network interactions outperform lexical models. Unlike previous work on deception detection, we find that adding syntax and grammar features to our models does not improve performance. Incorporating linguistic features improves classification results, however, social interaction features are most informative for finer-grained separation between four types of suspicious news posts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="volkova-etal-2017-separating">
<titleInfo>
<title>Separating Facts from Fiction: Linguistic Models to Classify Suspicious and Trusted News Posts on Twitter</title>
</titleInfo>
<name type="personal">
<namePart type="given">Svitlana</namePart>
<namePart type="family">Volkova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Shaffer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="given">Yea</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Hodas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Barzilay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pew research polls report 62 percent of U.S. adults get news on social media (Gottfried and Shearer, 2016). In a December poll, 64 percent of U.S. adults said that “made-up news” has caused a “great deal of confusion” about the facts of current events (Barthel et al., 2016). Fabricated stories in social media, ranging from deliberate propaganda to hoaxes and satire, contributes to this confusion in addition to having serious effects on global stability. In this work we build predictive models to classify 130 thousand news posts as suspicious or verified, and predict four sub-types of suspicious news – satire, hoaxes, clickbait and propaganda. We show that neural network models trained on tweet content and social network interactions outperform lexical models. Unlike previous work on deception detection, we find that adding syntax and grammar features to our models does not improve performance. Incorporating linguistic features improves classification results, however, social interaction features are most informative for finer-grained separation between four types of suspicious news posts.</abstract>
<identifier type="citekey">volkova-etal-2017-separating</identifier>
<identifier type="doi">10.18653/v1/P17-2102</identifier>
<location>
<url>https://aclanthology.org/P17-2102</url>
</location>
<part>
<date>2017-07</date>
<extent unit="page">
<start>647</start>
<end>653</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Separating Facts from Fiction: Linguistic Models to Classify Suspicious and Trusted News Posts on Twitter
%A Volkova, Svitlana
%A Shaffer, Kyle
%A Jang, Jin Yea
%A Hodas, Nathan
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F volkova-etal-2017-separating
%X Pew research polls report 62 percent of U.S. adults get news on social media (Gottfried and Shearer, 2016). In a December poll, 64 percent of U.S. adults said that “made-up news” has caused a “great deal of confusion” about the facts of current events (Barthel et al., 2016). Fabricated stories in social media, ranging from deliberate propaganda to hoaxes and satire, contributes to this confusion in addition to having serious effects on global stability. In this work we build predictive models to classify 130 thousand news posts as suspicious or verified, and predict four sub-types of suspicious news – satire, hoaxes, clickbait and propaganda. We show that neural network models trained on tweet content and social network interactions outperform lexical models. Unlike previous work on deception detection, we find that adding syntax and grammar features to our models does not improve performance. Incorporating linguistic features improves classification results, however, social interaction features are most informative for finer-grained separation between four types of suspicious news posts.
%R 10.18653/v1/P17-2102
%U https://aclanthology.org/P17-2102
%U https://doi.org/10.18653/v1/P17-2102
%P 647-653
Markdown (Informal)
[Separating Facts from Fiction: Linguistic Models to Classify Suspicious and Trusted News Posts on Twitter](https://aclanthology.org/P17-2102) (Volkova et al., ACL 2017)
ACL