@inproceedings{low-etal-2025-multimodal,
title = "Multimodal Fake News Detection Combining Social Network Features with Images and Text",
author = "Low, Lawrence Yung Hak and
Wu, Yen-Tsang and
Liu, Yan-Hong and
Wang, Jenq-Haur",
editor = "Chang, Kai-Wei and
Lu, Ke-Han and
Yang, Chih-Kai and
Tam, Zhi-Rui and
Chang, Wen-Yu and
Wang, Chung-Che",
booktitle = "Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)",
month = nov,
year = "2025",
address = "National Taiwan University, Taipei City, Taiwan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.rocling-main.28/",
pages = "266--276",
ISBN = "979-8-89176-379-1",
abstract = "The rapid development of social networks, coupled with the prevalence of Generative AI (GAI) in our society today, has led to a sharp increase in fake tweets and fake news on social media platforms. These fake media led to more in-depth research on fake news detection. At present, there are two mainstream methods used in detecting fake news, namely content-based fake news detection and propagation / network-based fake news detection. Early content-based detection method inputs an article{'}s content and uses a similarity algorithm to identify fake news. This method improved by using single-modality features such as images and text as input features. However, existing research shows that single-modality features alone cannot identify fake news efficiently. The most recent method then fuses multimodal features such as images and text, as features to be input into the model for classification purposes. The second propagation / network-based fake news detection method creates graphs or decision trees through social networks, treating them as features to be input into the model for classification purposes. In this study, we propose a multimodal fake news detection framework that combines these two mainstream methods. This framework not only uses images and text as input features but also combines social metadata features such as comments. The framework extracts these comments and builds them into a tree structure to obtain its features. Furthermore, we also propose different feature fusion methods which can achieve better results compared with the existing methods. Finally, we conducted ablation experiments and proved that each module is required to contribute to the framework{'}s overall performance. This clearly demonstrated the effectiveness of our proposed approach."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="low-etal-2025-multimodal">
<titleInfo>
<title>Multimodal Fake News Detection Combining Social Network Features with Images and Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lawrence</namePart>
<namePart type="given">Yung</namePart>
<namePart type="given">Hak</namePart>
<namePart type="family">Low</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yen-Tsang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan-Hong</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jenq-Haur</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kai-Wei</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ke-Han</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chih-Kai</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhi-Rui</namePart>
<namePart type="family">Tam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wen-Yu</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chung-Che</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">National Taiwan University, Taipei City, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-379-1</identifier>
</relatedItem>
<abstract>The rapid development of social networks, coupled with the prevalence of Generative AI (GAI) in our society today, has led to a sharp increase in fake tweets and fake news on social media platforms. These fake media led to more in-depth research on fake news detection. At present, there are two mainstream methods used in detecting fake news, namely content-based fake news detection and propagation / network-based fake news detection. Early content-based detection method inputs an article’s content and uses a similarity algorithm to identify fake news. This method improved by using single-modality features such as images and text as input features. However, existing research shows that single-modality features alone cannot identify fake news efficiently. The most recent method then fuses multimodal features such as images and text, as features to be input into the model for classification purposes. The second propagation / network-based fake news detection method creates graphs or decision trees through social networks, treating them as features to be input into the model for classification purposes. In this study, we propose a multimodal fake news detection framework that combines these two mainstream methods. This framework not only uses images and text as input features but also combines social metadata features such as comments. The framework extracts these comments and builds them into a tree structure to obtain its features. Furthermore, we also propose different feature fusion methods which can achieve better results compared with the existing methods. Finally, we conducted ablation experiments and proved that each module is required to contribute to the framework’s overall performance. This clearly demonstrated the effectiveness of our proposed approach.</abstract>
<identifier type="citekey">low-etal-2025-multimodal</identifier>
<location>
<url>https://aclanthology.org/2025.rocling-main.28/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>266</start>
<end>276</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multimodal Fake News Detection Combining Social Network Features with Images and Text
%A Low, Lawrence Yung Hak
%A Wu, Yen-Tsang
%A Liu, Yan-Hong
%A Wang, Jenq-Haur
%Y Chang, Kai-Wei
%Y Lu, Ke-Han
%Y Yang, Chih-Kai
%Y Tam, Zhi-Rui
%Y Chang, Wen-Yu
%Y Wang, Chung-Che
%S Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025)
%D 2025
%8 November
%I Association for Computational Linguistics
%C National Taiwan University, Taipei City, Taiwan
%@ 979-8-89176-379-1
%F low-etal-2025-multimodal
%X The rapid development of social networks, coupled with the prevalence of Generative AI (GAI) in our society today, has led to a sharp increase in fake tweets and fake news on social media platforms. These fake media led to more in-depth research on fake news detection. At present, there are two mainstream methods used in detecting fake news, namely content-based fake news detection and propagation / network-based fake news detection. Early content-based detection method inputs an article’s content and uses a similarity algorithm to identify fake news. This method improved by using single-modality features such as images and text as input features. However, existing research shows that single-modality features alone cannot identify fake news efficiently. The most recent method then fuses multimodal features such as images and text, as features to be input into the model for classification purposes. The second propagation / network-based fake news detection method creates graphs or decision trees through social networks, treating them as features to be input into the model for classification purposes. In this study, we propose a multimodal fake news detection framework that combines these two mainstream methods. This framework not only uses images and text as input features but also combines social metadata features such as comments. The framework extracts these comments and builds them into a tree structure to obtain its features. Furthermore, we also propose different feature fusion methods which can achieve better results compared with the existing methods. Finally, we conducted ablation experiments and proved that each module is required to contribute to the framework’s overall performance. This clearly demonstrated the effectiveness of our proposed approach.
%U https://aclanthology.org/2025.rocling-main.28/
%P 266-276
Markdown (Informal)
[Multimodal Fake News Detection Combining Social Network Features with Images and Text](https://aclanthology.org/2025.rocling-main.28/) (Low et al., ROCLING 2025)
ACL