Multimodal Emergent Fake News Detection via Meta Neural Process Networks

Wang, Yaqing; Ma, Fenglong; Wang, Haoyu; Jha, Kishlay; Gao, Jing

doi:10.1145/3447548.3467153

Cited by 85 publications

(112 citation statements)

References 32 publications

Supporting

Mentioning

110

Contrasting

Unclassified

Order By: Relevance

“…Raj and Meel [52] also utilized covNet for text and images but used the early fusion technique. Similarly, Wang et al [53] also employed CNN with an attention mechanism. Madhusudhan et al [54] utilized a similar approach, but they used SBERT and ResNet-18.…”

Section: Multi-modal Approachmentioning

confidence: 99%

FakedBits- Detecting Fake Information on Social Platforms using Multi-Modal Features

2023

KSII TIIS

View full text Add to dashboard Cite

Social media play a significant role in communicating information across the globe, connecting with loved ones, getting the news, communicating ideas, etc. However, a group of people uses social media to spread fake information, which has a bad impact on society. Therefore, minimizing fake news and its detection are the two primary challenges that need to be addressed. This paper presents a multi-modal deep learning technique to address the above challenges. The proposed modal can use and process visual and textual features. Therefore, it has the ability to detect fake information from visual and textual data. We used EfficientNet-B0 and a sentence transformer, respectively, for detecting counterfeit images and for textural learning. Feature embedding is performed at individual channels, whilst fusion is done at the last classification layer. The late fusion is applied intentionally to mitigate the noisy data that are generated by multi-modalities. Extensive experiments are conducted, and performance is evaluated against state-of-the-art methods. Three real-world benchmark datasets, such as MediaEval (Twitter), Weibo, and Fakeddit, are used for experimentation. Result reveals that the proposed modal outperformed the state-of-the-art methods and achieved an accuracy of 86.48%, 82.50%, and 88.80%, respectively, for MediaEval (Twitter), Weibo, and Fakeddit datasets.

show abstract

Section: Multi-modal Approachmentioning

confidence: 99%

FakedBits- Detecting Fake Information on Social Platforms using Multi-Modal Features

2023

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…Generally speaking, international news carries the most complex event logic as well as plentiful multimodal information [81]. To completely exploit the advantages of multimodal knowledge graphs, building a dataset using event logic from international news is a natural approach.…”

Section: Multimodel Knowledge Graphmentioning

confidence: 99%

UKnow: A Unified Knowledge Protocol for Common-Sense Reasoning and Vision-Language Pre-training

Gong¹,

Xie²,

Feng³

et al. 2023

Preprint

View full text Add to dashboard Cite

This work presents a unified knowledge protocol, called UKnow, which facilitates knowledge-based studies from the perspective of data. Particularly focusing on visual and linguistic modalities, we categorize data knowledge into five unit types, namely, in-image, intext, cross-image, cross-text, and image-text. Following this protocol, we collect, from public international news, a large-scale multimodal knowledge graph dataset that consists of 1,388,568 nodes (with 571,791 visionrelated ones) and 3,673,817 triplets. The dataset is also annotated with rich event tags, including 96 coarse labels and 9,185 fine labels, expanding its potential usage. To further verify that UKnow can serve as a standard protocol, we set up an efficient pipeline to help reorganize existing datasets under UKnow format. Finally, we benchmark the performance of some widely-used baselines on the tasks of common-sense reasoning and visionlanguage pre-training. Results on both our new dataset and the reformatted public datasets demonstrate the effectiveness of UKnow in knowledge organization and method evaluation. Code, dataset, conversion tool, and baseline models will be made public. (https://github. com/Gongggg/UKnow)

show abstract

“…Some methods focus on extracting textual representations [9], [10], [58], [60], [61]. In addition, visual features of news have been shown to be an important indicator for fake news detection [51], [62], [63]. As fake news publishers tend to use inflammatory and emotional expressions to draw reader's attention for a wide dissemination, style [39], [50], [64] and emotion [30], [31], [65] are useful patterns for fake news detection.…”

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.

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

Multimodal Emergent Fake News Detection via Meta Neural Process Networks

Cited by 85 publications

References 32 publications

FakedBits- Detecting Fake Information on Social Platforms using Multi-Modal Features

FakedBits- Detecting Fake Information on Social Platforms using Multi-Modal Features

UKnow: A Unified Knowledge Protocol for Common-Sense Reasoning and Vision-Language Pre-training

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

Contact Info

Product

Resources

About