@inproceedings{qi-etal-2023-two,
title = "Two Heads Are Better Than One: Improving Fake News Video Detection by Correlating with Neighbors",
author = "Qi, Peng and
Zhao, Yuyang and
Shen, Yufeng and
Ji, Wei and
Cao, Juan and
Chua, Tat-Seng",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.756",
doi = "10.18653/v1/2023.findings-acl.756",
pages = "11947--11959",
abstract = "The prevalence of short video platforms has spawned a lot of fake news videos, which have stronger propagation ability than textual fake news. Thus, automatically detecting fake news videos has been an important countermeasure in practice. Previous works commonly verify each news video individually with multimodal information. Nevertheless, news videos from different perspectives regarding the same event are commonly posted together, which contain complementary or contradictory information and thus can be used to evaluate each other mutually. To this end, we introduce a new and practical paradigm, i.e., cross-sample fake news video detection, and propose a novel framework, Neighbor-Enhanced fakE news video Detection (NEED), which integrates the neighborhood relationship of new videos belonging to the same event. NEED can be readily combined with existing single-sample detectors and further enhance their performances with the proposed graph aggregation (GA) and debunking rectification (DR) modules. Specifically, given the feature representations obtained from single-sample detectors, GA aggregates the neighborhood information with the dynamic graph to enrich the features of independent samples. After that, DR explicitly leverages the relationship between debunking videos and fake news videos to refute the candidate videos via textual and visual consistency. Extensive experiments on the public benchmark demonstrate that NEED greatly improves the performance of both single-modal (up to 8.34{\%} in accuracy) and multimodal (up to 4.97{\%} in accuracy) base detectors.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qi-etal-2023-two">
<titleInfo>
<title>Two Heads Are Better Than One: Improving Fake News Video Detection by Correlating with Neighbors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peng</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuyang</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufeng</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tat-Seng</namePart>
<namePart type="family">Chua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The prevalence of short video platforms has spawned a lot of fake news videos, which have stronger propagation ability than textual fake news. Thus, automatically detecting fake news videos has been an important countermeasure in practice. Previous works commonly verify each news video individually with multimodal information. Nevertheless, news videos from different perspectives regarding the same event are commonly posted together, which contain complementary or contradictory information and thus can be used to evaluate each other mutually. To this end, we introduce a new and practical paradigm, i.e., cross-sample fake news video detection, and propose a novel framework, Neighbor-Enhanced fakE news video Detection (NEED), which integrates the neighborhood relationship of new videos belonging to the same event. NEED can be readily combined with existing single-sample detectors and further enhance their performances with the proposed graph aggregation (GA) and debunking rectification (DR) modules. Specifically, given the feature representations obtained from single-sample detectors, GA aggregates the neighborhood information with the dynamic graph to enrich the features of independent samples. After that, DR explicitly leverages the relationship between debunking videos and fake news videos to refute the candidate videos via textual and visual consistency. Extensive experiments on the public benchmark demonstrate that NEED greatly improves the performance of both single-modal (up to 8.34% in accuracy) and multimodal (up to 4.97% in accuracy) base detectors.</abstract>
<identifier type="citekey">qi-etal-2023-two</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.756</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.756</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>11947</start>
<end>11959</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Two Heads Are Better Than One: Improving Fake News Video Detection by Correlating with Neighbors
%A Qi, Peng
%A Zhao, Yuyang
%A Shen, Yufeng
%A Ji, Wei
%A Cao, Juan
%A Chua, Tat-Seng
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F qi-etal-2023-two
%X The prevalence of short video platforms has spawned a lot of fake news videos, which have stronger propagation ability than textual fake news. Thus, automatically detecting fake news videos has been an important countermeasure in practice. Previous works commonly verify each news video individually with multimodal information. Nevertheless, news videos from different perspectives regarding the same event are commonly posted together, which contain complementary or contradictory information and thus can be used to evaluate each other mutually. To this end, we introduce a new and practical paradigm, i.e., cross-sample fake news video detection, and propose a novel framework, Neighbor-Enhanced fakE news video Detection (NEED), which integrates the neighborhood relationship of new videos belonging to the same event. NEED can be readily combined with existing single-sample detectors and further enhance their performances with the proposed graph aggregation (GA) and debunking rectification (DR) modules. Specifically, given the feature representations obtained from single-sample detectors, GA aggregates the neighborhood information with the dynamic graph to enrich the features of independent samples. After that, DR explicitly leverages the relationship between debunking videos and fake news videos to refute the candidate videos via textual and visual consistency. Extensive experiments on the public benchmark demonstrate that NEED greatly improves the performance of both single-modal (up to 8.34% in accuracy) and multimodal (up to 4.97% in accuracy) base detectors.
%R 10.18653/v1/2023.findings-acl.756
%U https://aclanthology.org/2023.findings-acl.756
%U https://doi.org/10.18653/v1/2023.findings-acl.756
%P 11947-11959
Markdown (Informal)
[Two Heads Are Better Than One: Improving Fake News Video Detection by Correlating with Neighbors](https://aclanthology.org/2023.findings-acl.756) (Qi et al., Findings 2023)
ACL