<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2025-fake">
    <titleInfo>
        <title>A Fake News Detection Model Utilizing Graph Neural Networks to Capture Writing Styles</title>
    </titleInfo>
    <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">Lawrence</namePart>
        <namePart type="given">Y</namePart>
        <namePart type="given">H</namePart>
        <namePart type="family">Low</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>本文提出 CWSMN(Capture Writing Style Multi-Graph Network),一個以圖神經網路為基礎的早期假新聞偵測方法,透過捕捉寫作風格克服傳統語意內容與傳播特徵方法在標註稀缺與跨域泛化不足下的限制。CWSMN 結合文體分析、語意嵌入與多圖融合:以 Bi-GRU 進行上下文初始化,採用 GAT 進行注意力導向的圖聚合,並以 LDA 建構主題圖,同時以輕量級前饋分類器輸出預測。於多個資料集之實驗顯示,CWSMN 對比 BERT、ALBERT 與 GraphSAINT 等強基準皆有穩定超越;在未知來源的 Source-CV 場景尤為顯著,證明其於低資源與跨領域環境之穩健泛化能力,並實現不依賴傳播的早期偵測,實驗結果證實本方法在樣本稀缺與未知來源條件下,仍能達成有效的早期偵測。</abstract>
    <identifier type="citekey">wu-etal-2025-fake</identifier>
    <location>
        <url>https://aclanthology.org/2025.rocling-main.30/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>286</start>
            <end>295</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T A Fake News Detection Model Utilizing Graph Neural Networks to Capture Writing Styles
%A Wu, Yen-Tsang
%A Low, Lawrence Y. H.
%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 wu-etal-2025-fake
%X 本文提出 CWSMN(Capture Writing Style Multi-Graph Network),一個以圖神經網路為基礎的早期假新聞偵測方法,透過捕捉寫作風格克服傳統語意內容與傳播特徵方法在標註稀缺與跨域泛化不足下的限制。CWSMN 結合文體分析、語意嵌入與多圖融合:以 Bi-GRU 進行上下文初始化,採用 GAT 進行注意力導向的圖聚合,並以 LDA 建構主題圖,同時以輕量級前饋分類器輸出預測。於多個資料集之實驗顯示,CWSMN 對比 BERT、ALBERT 與 GraphSAINT 等強基準皆有穩定超越;在未知來源的 Source-CV 場景尤為顯著,證明其於低資源與跨領域環境之穩健泛化能力,並實現不依賴傳播的早期偵測,實驗結果證實本方法在樣本稀缺與未知來源條件下,仍能達成有效的早期偵測。
%U https://aclanthology.org/2025.rocling-main.30/
%P 286-295

Markdown (Informal)

[A Fake News Detection Model Utilizing Graph Neural Networks to Capture Writing Styles](https://aclanthology.org/2025.rocling-main.30/) (Wu et al., ROCLING 2025)

• A Fake News Detection Model Utilizing Graph Neural Networks to Capture Writing Styles (Wu et al., ROCLING 2025)

ACL

• Yen-Tsang Wu, Lawrence Y. H Low, and Jenq-Haur Wang. 2025. A Fake News Detection Model Utilizing Graph Neural Networks to Capture Writing Styles. In Proceedings of the 37th Conference on Computational Linguistics and Speech Processing (ROCLING 2025), pages 286–295, National Taiwan University, Taipei City, Taiwan. Association for Computational Linguistics.