MMCoVaR: Multimodal COVID-19 vaccine focused data repository for fake news detection and a baseline architecture for classification

Mingxuan Chen; Xinqiao Chu; K. P. Subbalakshmi

doi:10.1145/3487351.3488346

MMCoVaR: Multimodal COVID-19 vaccine focused data repository for fake news detection and a baseline architecture for classification

Mingxuan Chen
, Xinqiao Chu
, K. P. Subbalakshmi

Department of Electrical and Computer Engineering

Stevens Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

29 Scopus citations

Abstract

The outbreak of COVID-19 has resulted in an "infodemic"that has encouraged the propagation of misinformation about COVID-19 and cure methods which, in turn, could negatively affect the adoption of recommended public health measures in the larger population. In this paper, we provide a new multimodal (consisting of images, text and temporal information) labeled dataset containing news articles and tweets on the COVID-19 vaccine. We collected 2,593 news articles from 80 publishers for one year between Feb 16th 2020 to May 8th 2021 and 24184 Twitter posts (collected between April 17th 2021 to May 8th 2021). We combine ratings from two news media ranking sites: Medias Bias Chart and Media Bias/Fact Check (MBFC) to classify the news dataset into two levels of credibility: reliable and unreliable. The combination of two filters allows for higher precision of labeling. We also propose a stance detection mechanism to annotate tweets into three levels of credibility: reliable, unreliable and inconclusive. We provide several statistics as well as other analytics like, publisher distribution, publication date distribution, topic analysis, etc. We also provide a novel architecture that classifies the news data into misinformation or truth to provide a baseline performance for this dataset. We find that the proposed architecture has an F-Score of 0.919 and accuracy of 0.882 for fake news detection. Furthermore, we provide benchmark performance for misinformation detection on tweet dataset. This new multimodal dataset can be used in research on COVID-19 vaccine, including misinformation detection, influence of fake COVID-19 vaccine information, etc.

Original language	English
Title of host publication	Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021
Editors	Michele Coscia, Alfredo Cuzzocrea, Kai Shu
Pages	31-38
Number of pages	8
ISBN (Electronic)	9781450391283
DOIs	https://doi.org/10.1145/3487351.3488346
State	Published - 8 Nov 2021
Event	13th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021 - Virtual, Online, Netherlands Duration: 8 Nov 2021 → …

Publication series

Name	Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021

Conference

Conference	13th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021
Country/Territory	Netherlands
City	Virtual, Online
Period	8/11/21 → …

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

COVID-19 vaccine
explainable model
fake news detection
misinformation
modular architecture
multimodal data repository

Access to Document

10.1145/3487351.3488346

Cite this

Chen, M., Chu, X., & Subbalakshmi, K. P. (2021). MMCoVaR: Multimodal COVID-19 vaccine focused data repository for fake news detection and a baseline architecture for classification. In M. Coscia, A. Cuzzocrea, & K. Shu (Eds.), Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021 (pp. 31-38). (Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021). https://doi.org/10.1145/3487351.3488346

Chen, Mingxuan ; Chu, Xinqiao ; Subbalakshmi, K. P. / MMCoVaR : Multimodal COVID-19 vaccine focused data repository for fake news detection and a baseline architecture for classification. Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021. editor / Michele Coscia ; Alfredo Cuzzocrea ; Kai Shu. 2021. pp. 31-38 (Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021).

@inproceedings{feb16a8b040a47e18a093ad6ebf14fda,

title = "MMCoVaR: Multimodal COVID-19 vaccine focused data repository for fake news detection and a baseline architecture for classification",

abstract = "The outbreak of COVID-19 has resulted in an {"}infodemic{"}that has encouraged the propagation of misinformation about COVID-19 and cure methods which, in turn, could negatively affect the adoption of recommended public health measures in the larger population. In this paper, we provide a new multimodal (consisting of images, text and temporal information) labeled dataset containing news articles and tweets on the COVID-19 vaccine. We collected 2,593 news articles from 80 publishers for one year between Feb 16th 2020 to May 8th 2021 and 24184 Twitter posts (collected between April 17th 2021 to May 8th 2021). We combine ratings from two news media ranking sites: Medias Bias Chart and Media Bias/Fact Check (MBFC) to classify the news dataset into two levels of credibility: reliable and unreliable. The combination of two filters allows for higher precision of labeling. We also propose a stance detection mechanism to annotate tweets into three levels of credibility: reliable, unreliable and inconclusive. We provide several statistics as well as other analytics like, publisher distribution, publication date distribution, topic analysis, etc. We also provide a novel architecture that classifies the news data into misinformation or truth to provide a baseline performance for this dataset. We find that the proposed architecture has an F-Score of 0.919 and accuracy of 0.882 for fake news detection. Furthermore, we provide benchmark performance for misinformation detection on tweet dataset. This new multimodal dataset can be used in research on COVID-19 vaccine, including misinformation detection, influence of fake COVID-19 vaccine information, etc.",

keywords = "COVID-19 vaccine, explainable model, fake news detection, misinformation, modular architecture, multimodal data repository",

author = "Mingxuan Chen and Xinqiao Chu and Subbalakshmi, \{K. P.\}",

note = "Publisher Copyright: {\textcopyright} 2021 ACM.; 13th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021 ; Conference date: 08-11-2021",

year = "2021",

month = nov,

day = "8",

doi = "10.1145/3487351.3488346",

language = "English",

series = "Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021",

pages = "31--38",

editor = "Michele Coscia and Alfredo Cuzzocrea and Kai Shu",

booktitle = "Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021",

}

Chen, M, Chu, X & Subbalakshmi, KP 2021, MMCoVaR: Multimodal COVID-19 vaccine focused data repository for fake news detection and a baseline architecture for classification. in M Coscia, A Cuzzocrea & K Shu (eds), Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021. Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021, pp. 31-38, 13th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021, Virtual, Online, Netherlands, 8/11/21. https://doi.org/10.1145/3487351.3488346

MMCoVaR: Multimodal COVID-19 vaccine focused data repository for fake news detection and a baseline architecture for classification. / Chen, Mingxuan; Chu, Xinqiao; Subbalakshmi, K. P.
Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021. ed. / Michele Coscia; Alfredo Cuzzocrea; Kai Shu. 2021. p. 31-38 (Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - MMCoVaR

T2 - 13th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021

AU - Chen, Mingxuan

AU - Chu, Xinqiao

AU - Subbalakshmi, K. P.

PY - 2021/11/8

Y1 - 2021/11/8

N2 - The outbreak of COVID-19 has resulted in an "infodemic"that has encouraged the propagation of misinformation about COVID-19 and cure methods which, in turn, could negatively affect the adoption of recommended public health measures in the larger population. In this paper, we provide a new multimodal (consisting of images, text and temporal information) labeled dataset containing news articles and tweets on the COVID-19 vaccine. We collected 2,593 news articles from 80 publishers for one year between Feb 16th 2020 to May 8th 2021 and 24184 Twitter posts (collected between April 17th 2021 to May 8th 2021). We combine ratings from two news media ranking sites: Medias Bias Chart and Media Bias/Fact Check (MBFC) to classify the news dataset into two levels of credibility: reliable and unreliable. The combination of two filters allows for higher precision of labeling. We also propose a stance detection mechanism to annotate tweets into three levels of credibility: reliable, unreliable and inconclusive. We provide several statistics as well as other analytics like, publisher distribution, publication date distribution, topic analysis, etc. We also provide a novel architecture that classifies the news data into misinformation or truth to provide a baseline performance for this dataset. We find that the proposed architecture has an F-Score of 0.919 and accuracy of 0.882 for fake news detection. Furthermore, we provide benchmark performance for misinformation detection on tweet dataset. This new multimodal dataset can be used in research on COVID-19 vaccine, including misinformation detection, influence of fake COVID-19 vaccine information, etc.

AB - The outbreak of COVID-19 has resulted in an "infodemic"that has encouraged the propagation of misinformation about COVID-19 and cure methods which, in turn, could negatively affect the adoption of recommended public health measures in the larger population. In this paper, we provide a new multimodal (consisting of images, text and temporal information) labeled dataset containing news articles and tweets on the COVID-19 vaccine. We collected 2,593 news articles from 80 publishers for one year between Feb 16th 2020 to May 8th 2021 and 24184 Twitter posts (collected between April 17th 2021 to May 8th 2021). We combine ratings from two news media ranking sites: Medias Bias Chart and Media Bias/Fact Check (MBFC) to classify the news dataset into two levels of credibility: reliable and unreliable. The combination of two filters allows for higher precision of labeling. We also propose a stance detection mechanism to annotate tweets into three levels of credibility: reliable, unreliable and inconclusive. We provide several statistics as well as other analytics like, publisher distribution, publication date distribution, topic analysis, etc. We also provide a novel architecture that classifies the news data into misinformation or truth to provide a baseline performance for this dataset. We find that the proposed architecture has an F-Score of 0.919 and accuracy of 0.882 for fake news detection. Furthermore, we provide benchmark performance for misinformation detection on tweet dataset. This new multimodal dataset can be used in research on COVID-19 vaccine, including misinformation detection, influence of fake COVID-19 vaccine information, etc.

KW - COVID-19 vaccine

KW - explainable model

KW - fake news detection

KW - misinformation

KW - modular architecture

KW - multimodal data repository

UR - https://www.scopus.com/pages/publications/85124405047

UR - https://www.scopus.com/pages/publications/85124405047#tab=citedBy

U2 - 10.1145/3487351.3488346

DO - 10.1145/3487351.3488346

M3 - Conference contribution

AN - SCOPUS:85124405047

T3 - Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021

SP - 31

EP - 38

BT - Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021

A2 - Coscia, Michele

A2 - Cuzzocrea, Alfredo

A2 - Shu, Kai

Y2 - 8 November 2021

ER -

Chen M, Chu X, Subbalakshmi KP. MMCoVaR: Multimodal COVID-19 vaccine focused data repository for fake news detection and a baseline architecture for classification. In Coscia M, Cuzzocrea A, Shu K, editors, Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021. 2021. p. 31-38. (Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2021). doi: 10.1145/3487351.3488346

MMCoVaR: Multimodal COVID-19 vaccine focused data repository for fake news detection and a baseline architecture for classification

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this