CoChat

A multimodal fake news detection model based on crossmodal attention residual and multichannel convolutional neural networks

Song, Chenguang, Ning, Nianwen, Zhang, Yunlei, Wu, Bin · 2021 · Information Processing & Management
Cited by 248

The DOI matches its Crossref record; 19 of the 19 references it cites were found in a registry or an index.

Abstract

In recent years, social media has increasingly become one of the popular ways for people to consume news. As proliferation of fake news on social media has the negative impacts on individuals and society, automatic fake news detection has been explored by different research communities for combating fake news. With the development of multimedia technology, there is a phenomenon that cannot be ignored is that more and more social media news contains information with different modalities, e.g., texts, pictures and videos. The multiple information modalities show more evidence of the happening of news events and present new opportunities to detect features in fake news. First, for multimodal fake news detection task, it is a challenge of keeping the unique properties for each modality while fusing the relevant information between different modalities. Second, for some news, the information fusion between different modalities may produce the noise information which affects model’s performance. Unfortunately, existing methods fail to handle these challenges. To address these problems, we propose a multimodal fake news detection framework based on Crossmodal Attention Residual and Multichannel convolutional neural Networks (CARMN). The Crossmodal Attention Residual Network (CARN) can selectively extract the relevant information related to a target modality from another source modality while maintaining the unique information of the target modality. The Multichannel Convolutional neural Network (MCN) can mitigate the influence of noise information which may be generated by crossmodal fusion component by extracting textual feature representation from original and fused textual information simultaneously. We conduct extensive experiments on four real-world datasets and demonstrate that the proposed model outperforms the state-of-the-art methods and learns more discriminable feature representations.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.ipm.2020.102437

Cites

19 of 19 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Cited by

See all 248

Metadata

Authors
Song, C., Ning, N., Zhang, Y., & Wu, B.
Venue
Information Processing & Management
Publisher
Elsevier BV
Published
2021-01
Volume
58
Issue
1
Pages
102437
ISSN
  • 0020-0271 (ISSN-L)
  • 0306-4573
OpenAlex
W3106237638
Cited by
248
References
19
FWCI
37.35
Type
journal article
Language
en
Open access
closed

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.