Leverage knowledge graph and GCN for fine-grained-level clickbait detection.

IF 1.2 4区 心理学 Q3 PSYCHOLOGY, MULTIDISCIPLINARY Hispanic Journal of Behavioral Sciences Pub Date : 2022-01-01 Epub Date: 2022-03-16 DOI:10.1007/s11280-022-01032-3
Mengxi Zhou, Wei Xu, Wenping Zhang, Qiqi Jiang
{"title":"Leverage knowledge graph and GCN for fine-grained-level clickbait detection.","authors":"Mengxi Zhou, Wei Xu, Wenping Zhang, Qiqi Jiang","doi":"10.1007/s11280-022-01032-3","DOIUrl":null,"url":null,"abstract":"<p><p>Clickbait is the use of an enticing title as bait to deceive users to click. However, the corresponding content is often disappointing, infuriating or even deceitful. This practice has brought serious damage to our social trust, especially to online media, which is one of the most important channels for information acquisition in our daily life. Currently, clickbait is spreading on the internet and causing serious damage to society. However, research on clickbait detection has not yet been well performed. Almost all existing research treats clickbait detection as a binary classification task and only uses the title as the input. This shallow usage of information and detection technology not only suffers from low performance in real detection (e.g., it is easy to bypass) but is also difficult to use in further research (e.g., potential empirical studies). In this work, we proposed a novel clickbait detection model that incorporated a knowledge graph, a graph convolutional network and a graph attention network to conduct fine-grained-level clickbait detection. According to experiments using a real dataset, our novel proposed model outperformed classical and state-of-the-art baselines. In addition, certain explainability can also be achieved in our model through the graph attention network. Our fine-grained-level results can provide a measurement foundation for future empirical study. To the best of our knowledge, this is the first attempt to incorporate a knowledge graph and deep learning technique to detect clickbait and achieve explainability.</p>","PeriodicalId":13072,"journal":{"name":"Hispanic Journal of Behavioral Sciences","volume":"17 1","pages":"1243-1258"},"PeriodicalIF":1.2000,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8924577/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Hispanic Journal of Behavioral Sciences","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1007/s11280-022-01032-3","RegionNum":4,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2022/3/16 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"PSYCHOLOGY, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

Clickbait is the use of an enticing title as bait to deceive users to click. However, the corresponding content is often disappointing, infuriating or even deceitful. This practice has brought serious damage to our social trust, especially to online media, which is one of the most important channels for information acquisition in our daily life. Currently, clickbait is spreading on the internet and causing serious damage to society. However, research on clickbait detection has not yet been well performed. Almost all existing research treats clickbait detection as a binary classification task and only uses the title as the input. This shallow usage of information and detection technology not only suffers from low performance in real detection (e.g., it is easy to bypass) but is also difficult to use in further research (e.g., potential empirical studies). In this work, we proposed a novel clickbait detection model that incorporated a knowledge graph, a graph convolutional network and a graph attention network to conduct fine-grained-level clickbait detection. According to experiments using a real dataset, our novel proposed model outperformed classical and state-of-the-art baselines. In addition, certain explainability can also be achieved in our model through the graph attention network. Our fine-grained-level results can provide a measurement foundation for future empirical study. To the best of our knowledge, this is the first attempt to incorporate a knowledge graph and deep learning technique to detect clickbait and achieve explainability.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用知识图谱和 GCN 进行细粒度点击诱饵检测。
点击诱饵是指使用诱人的标题作为诱饵,欺骗用户点击。然而,相应的内容却往往令人失望、愤怒甚至是欺骗。这种做法严重损害了我们的社会信任,尤其是作为日常生活中获取信息最重要渠道之一的网络媒体。目前,点击诱饵正在互联网上蔓延,对社会造成了严重危害。然而,关于点击诱饵检测的研究还不够完善。几乎所有现有研究都将点击诱饵检测视为二元分类任务,仅将标题作为输入。这种对信息和检测技术的浅层使用不仅在实际检测中性能低下(如容易被绕过),而且难以用于进一步的研究(如潜在的实证研究)。在这项工作中,我们提出了一种新颖的点击诱饵检测模型,该模型结合了知识图谱、图卷积网络和图注意力网络来进行细粒度的点击诱饵检测。根据使用真实数据集进行的实验,我们提出的新型模型优于经典模型和最先进的基线模型。此外,通过图注意力网络,我们的模型还实现了一定的可解释性。我们的细粒度结果可以为未来的实证研究提供测量基础。据我们所知,这是首次尝试结合知识图谱和深度学习技术来检测点击诱饵并实现可解释性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Hispanic Journal of Behavioral Sciences
Hispanic Journal of Behavioral Sciences PSYCHOLOGY, MULTIDISCIPLINARY-
CiteScore
2.70
自引率
0.00%
发文量
7
期刊介绍: The Hispanic Journal of Behavioral Sciences publishes empirical articles, multiple case study reports, critical reviews of literature, conceptual articles, reports of new instruments, and scholarly notes of theoretical or methodological interest to Hispanic populations. The multidisciplinary focus of the HJBS includes the fields of anthropology, economics, education, linguistics, political science, psychology, psychiatry, public health, and sociology.
期刊最新文献
Latinx Immigrant Health: Does Immigrants’ Perceptions of Integration Protect their Health? Anticipating Stress During the COVID-19 Pandemic: Mental Health Among Latinx Young Adults The Maternal Guilt of Working Latina Mothers: A Qualitative Study Bilingual Latina Siblings Supporting Siblings: Shared Reading as a Context for Supporting Cognitive Self-Regulation Associations Between Negative Context of Reception and Depressive Symptoms Among Immigrant Latino Men: The Moderating Effect of Machismo and Hispanicism
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1