Mid Sweden University

miun.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Classifying COVID-19 Disinformation on Twitter using a Convolutional Neural Network
Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology.
Mid Sweden University, Faculty of Science, Technology and Media, Department of Information Systems and Technology. (RCR, FODI)ORCID iD: 0000-0003-4869-5094
2022 (English)In: Proceedings of the 8th International Conference on Information Systsms Security and Privacy (ICISSP) / [ed] Mori, P Lenzini, G Furnell, S, SciTePress, 2022, p. 264-272Conference paper, Published paper (Refereed)
Abstract [en]

Disinformation regarding COVID-19 is spreading rapidly on social media platforms and can cause undesirable consequences for people who rely on such content. To combat disinformation, several platform providers have implemented intelligent systems to detect disinformation and provide measurements that apprise users of the quality of information being disseminated on social media platforms. For this purpose, intelligent systems employing deep learning approaches are often applied, hence, their effectivity requires closer analysis. The study begins with a thorough literature review regarding the concept of disinformation and its classification. This paper models and evaluates a disinformation detector that uses a convolutional neural network to classify samples of social media content. The evaluation of the proposed deep learning model showed that it performed well overall in discriminating the fake-labelled tweets from the real-labelled tweets; the model yielded an accuracy score of 97.2%, a precision score of 95.7% and a recall score of 99.8%. Consequently, the paper contributes an effective disinformation detector, which can be used as a tool to combat the substantial volume of disinformation scattered throughout social media platforms. A more standardised feature extraction for disinformation cases should be the subject of subsequent research.

Place, publisher, year, edition, pages
SciTePress, 2022. p. 264-272
Keywords [en]
Deep Learning, COVID-19, Twitter Data, Intelligent Systems, Disinformation, Fake News, Convolutional Neural Network, CNN
National Category
Information Systems Information Systems, Social aspects
Identifiers
URN: urn:nbn:se:miun:diva-45736DOI: 10.5220/0010774800003120ISI: 000818770500023Scopus ID: 2-s2.0-85176317805ISBN: 978-989-758-553-1 (print)OAI: oai:DiVA.org:miun-45736DiVA, id: diva2:1685237
Conference
8th International Conference on Information Systems Security and Privacy (ICISSP), FEB 09-11, 2022, ELECTR NETWORK
Available from: 2022-08-02 Created: 2022-08-02 Last updated: 2023-11-20Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Große, Christine

Search in DiVA

By author/editor
Große, Christine
By organisation
Department of Information Systems and Technology
Information SystemsInformation Systems, Social aspects

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 226 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf