User Preference-aware Fake News Detection

Dou, Yingtong; Shu, Kai; Xia, Congying; Yu, Philip S.; Sun, Lichao

doi:10.1145/3404835.3462990

Cited by 158 publications

(41 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Propagation networks have been testified their effectiveness for fake news detection [70], [71], [72]. In addition, user profile [73], [74] and crowd feedbacks [53], [75] are also important patterns to detect fake news.…”

Section: Related Workmentioning

confidence: 99%

Memory-Guided Multi-View Multi-Domain Fake News Detection

Zhu

Sheng

Cao

et al. 2022

IEEE Trans. Knowl. Data Eng.

Self Cite

View full text Add to dashboard Cite

The wide spread of fake news is increasingly threatening both individuals and society. Great efforts have been made for automatic fake news detection on a single domain (e.g., politics). However, correlations exist commonly across multiple news domains, and thus it is promising to simultaneously detect fake news of multiple domains. Based on our analysis, we pose two challenges in multi-domain fake news detection: 1) domain shift, caused by the discrepancy among domains in terms of words, emotions, styles, etc. 2) domain labeling incompleteness, stemming from the real-world categorization that only outputs one single domain label, regardless of topic diversity of a news piece. In this paper, we propose a Memory-guided Multi-view Multi-domain Fake News Detection Framework (M 3 FEND) to address these two challenges. We model news pieces from a multi-view perspective, including semantics, emotion, and style. Specifically, we propose a Domain Memory Bank to enrich domain information which could discover potential domain labels based on seen news pieces and model domain characteristics. Then, with enriched domain information as input, a Domain Adapter could adaptively aggregate discriminative information from multiple views for news in various domains. Extensive offline experiments on English and Chinese datasets demonstrate the effectiveness of M 3 FEND, and online tests verify its superiority in practice. Our code is available at https://github.com/ICTMCG/M3FEND.

show abstract

Section: Related Workmentioning

confidence: 99%

Memory-Guided Multi-View Multi-Domain Fake News Detection

Zhu

Sheng

Cao

et al. 2022

IEEE Trans. Knowl. Data Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

“…For example, Chen et al [50] extracted social homophily, influence, and susceptibility of users from the user interaction network for rumor detection. Dou et al [51] proposed a user preference-aware rumor detection model to learn user endogenous preference and exogenous context from users' historical posts and reply network, respectively.…”

Section: Deep Learning-based Approachesmentioning

confidence: 99%

Multi-view learning with distinguishable feature fusion for rumor detection

Chen

Zhang

Trajcevski

et al. 2022

Knowledge-Based Systems

View full text Add to dashboard Cite

“…Moreover, building a news propagation graph based on users' media platform engagement information. Since the previous work [35,36,37] proved that combining the user features with the news propagation graph is able to improve the performance of detecting fake news, in this way, this paper [32] proposes a framework called User Preference-aware Fake Detection (UPFD), which fuses endogenous and exogenous information using GNN. Hence, the UPFD predicts the credibility of news content on the social media platform.…”

Section: Deep Learning Approachmentioning

confidence: 99%

“…The inner workings of the network are always a mystery that is troubling the research community since deep learning has become popular. This section describes the model architecture of two deep learning techniques established by authors in [23,32].…”

Section: Deep Learning Modelmentioning

confidence: 99%

Misreporting and Fake News Detection Techniques on the Social Media Platform

Feng¹

2022

HSET

View full text Add to dashboard Cite

One of the major concerns nowadays is the rapid spreading of fake news or unverified information on all kinds of social media. Misinformation and disinformation on the digital media of news distribution have brought significant negative impacts to our community, which the traditional techniques can no longer detect and deal with it effectively. It is urgent to squelch fake news immediately to limit its impact on the economy and society. As deep learning techniques continue developing in recent decades, scholars successfully deployed deep neural networks on fake news detection tasks. The first noticeable thing is to admit that the fake news detection task has made significant accomplishments as fast as we hoped. It is necessary to study further and broadly review the state-of-the-art fake news detection approaches. In this review paper, we survey several distinct deep learning techniques and provide a comprehensive review of automatic fake news detection classification tasks and the datasets and models used, demonstrating the performance evaluation on different approaches. We have also analyzed the potential challenge we encountered in fake news detection.

show abstract

User Preference-aware Fake News Detection

Cited by 158 publications

References 11 publications

Memory-Guided Multi-View Multi-Domain Fake News Detection

Memory-Guided Multi-View Multi-Domain Fake News Detection

Multi-view learning with distinguishable feature fusion for rumor detection

Misreporting and Fake News Detection Techniques on the Social Media Platform

Contact Info

Product

Resources

About