EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MCred: multi-modal message credibility for fake news detection using BERT and CNN

Pawan Kumar Verma iD, Prateek Agrawal, Vishu Madaan, Radu Prodan

Journal of Ambient Intelligence and Humanized Computing · 2023-08 · 14 (8) · 10617-10629

DOI: 10.1007/s12652-022-04338-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Ambient Intelligence and Humanized Computing, online erschienen am 27.07.2022. Verfasst von Pawan Kumar Verma und 3 weiteren Autor:innen. Beteiligte Einrichtung: Present Address: Lovely Professional University, Phagwara, India. Die Arbeit wurde bisher 59-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: h2020 european institute of innovation and technology, University of Klagenfurt.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Online social media enables low cost, easy access, rapid propagation, and easy communication of information, including spreading low-quality fake news. Fake news has become a huge threat to every sector in society, and resulting in decrements in the trust quotient for media and leading the audience into bewilderment. In this paper, we proposed a new framework called M essage Cred ibility (MCred) for fake news detection that utilizes the benefits of local and global text semantics. This framework is the fusion of Bidirectional Encoder Representations from Transformers (BERT) using the relationship between words in sentences for global text semantics, and Convolutional Neural Networks (CNN) using N-gram features for local text semantics. We demonstrate through experimental results a popular Kaggle dataset that MCred improves the accuracy over a state-of-the-art model by 1.10% thanks to its combination of local and global text semantics.

Schlagwörter

Stichwörter der Autor:innen

Convolutional neural networkDeep learningDense networkFake news classificationGlobal semanticNatural language processingSocial media disinformationText classificationlocal semantic

Autor:innen und Institutionen

  • Present Address: Lovely Professional University, Phagwara, India.
  • MIT Art, Design and Technology University, Pune, India.
  • University of Klagenfurt, Klagenfurt, Austria.

ORCID-Profile: Pawan Kumar Verma

Förderung

  • h2020 european institute of innovation and technology
  • University of Klagenfurt

Zitieren

APA

Verma, P. K., Agrawal, P., Madaan, V., & Prodan, R. (2023). MCred: multi-modal message credibility for fake news detection using BERT and CNN. Journal of Ambient Intelligence and Humanized Computing, 14(8), 10617-10629. https://doi.org/10.1007/s12652-022-04338-2

Vancouver

Verma PK, Agrawal P, Madaan V, Prodan R. MCred: multi-modal message credibility for fake news detection using BERT and CNN. Journal of Ambient Intelligence and Humanized Computing. 2023;14(8):10617-10629. doi:10.1007/s12652-022-04338-2

BibTeX
@article{Verma2023,
  author = {Verma, Pawan Kumar and Agrawal, Prateek and Madaan, Vishu and Prodan, Radu},
  title = {MCred: multi-modal message credibility for fake news detection using BERT and CNN},
  journal = {Journal of Ambient Intelligence and Humanized Computing},
  year = {2023},
  volume = {14},
  number = {8},
  pages = {10617--10629},
  doi = {10.1007/s12652-022-04338-2}
}
Kostenlos starten →