Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023;6(1):19-57.
doi: 10.1007/s42001-022-00189-1. Epub 2022 Nov 27.

Enhanced sentiment analysis regarding COVID-19 news from global channels

Waseem Ahmad  1 , Bang Wang  1 , Philecia Martin  1 , Minghua Xu  2 , Han Xu  2
Affiliations

Enhanced sentiment analysis regarding COVID-19 news from global channels

Waseem Ahmad et al. J Comput Soc Sci. 2023.

Abstract

For a healthy society to exist, it is crucial for the media to focus on disease-related issues so that more people are widely aware of them and reduce health risks. Recently, deep neural networks have become a popular tool for textual sentiment analysis, which can provide valuable insights and real-time monitoring and analysis regarding health issues. In this paper, as part of an effort to develop an effective model that can elicit public sentiment on COVID-19 news, we propose a novel approach Cov-Att-BiLSTM for sentiment analysis of COVID-19 news headlines using deep neural networks. We integrate attention mechanisms, embedding techniques, and semantic level data labeling into the prediction process to enhance the accuracy. To evaluate the proposed approach, we compared it to several deep and machine learning classifiers using various metrics of categorization efficiency and prediction quality, and the experimental results demonstrate its superiority with 0.931 testing accuracy. Furthermore, 73,138 pandemic-related tweets posted on six global channels were analyzed by the proposed approach, which accurately reflects global coverage of COVID-19 news and vaccination.

Keywords: COVID-19; Deep learning; News media; Sentiment analysis; Vaccine.

PubMed Disclaimer

Conflict of interest statement

Conflict of interestOn behalf of all authors, the corresponding author states that there is no conflict of interest.

Figures

Fig. 1
Fig. 1
Neural network illustration of Cov-Att-BiLSTM
Fig. 2
Fig. 2
A visual representation of attention weights in sample sentences
Fig. 3
Fig. 3
Performance comparison of ROBERTa-base, Vader, Textlob, and our model Cov-Att-BiLSTM in terms of Accmarco, Premarco, Recmarco, and F1marco in the manual-label dataset
Fig. 4
Fig. 4
Distribution of COVID-19 news sentiments in news channels
Fig. 5
Fig. 5
Distribution of vaccine news sentiments in news channels
Fig. 6
Fig. 6
Word clouds for the most frequently used words in COVID-19 negative news
Fig. 7
Fig. 7
Distribution of COVID-19 tweet sentiments across news channels over the quarters of 2020–2021
Fig. 8
Fig. 8
Distribution of vaccine tweet sentiments across news channels over the quarters of 2020–2021
Fig. 9
Fig. 9
Distribution of sentiments regarding vaccine types in news channels
Fig. 10
Fig. 10
Distribution of sentiments regarding COVID-19 news in different countries
Fig. 11
Fig. 11
Analysis of sentiments regarding COVID news coverage of channels in different countries. a Negative sentiments. b Natural sentiments. c Positive sentiments
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Abercrombie G, Batista-Navarro R. Sentiment and position-taking analysis of parliamentary debates: a systematic literature review. Journal of Computational Social Science. 2020;3(1):245–270. doi: 10.1007/s42001-019-00060-w. - DOI
    1. Agarwal A, Agarwal B, Harjule P, Agarwal A. Predictive and preventive measures for Covid-19 pandemic. Singapore: Springer; 2021. Mental health analysis of students in major cities of India during COVID-19; pp. 51–67.
    1. Ahmad W, Wang B, Han Xu, Minghua Xu, Zeng Z. Topics, sentiments, and emotions triggered by COVID-19-related tweets from iran and turkey official news agencies. SN Computer Science. 2021;2(5):1–19. doi: 10.1007/s42979-021-00789-0. - DOI - PMC - PubMed
    1. Alam, K. N., Khan, M. S., Dhruba, A. R., Khan, M. M., Al-Amri, J. F., Masud, M., & Rawashdeh, M. (2021). Deep learning-based sentiment analysis of COVID-19 vaccination responses from twitter data. Computational and Mathematical Methods in Medicine, 2021. - PMC - PubMed
    1. Aljabri M, Chrouf SM, Alzahrani NA, Alghamdi L, Alfehaid R, Alqarawi R, Alhuthayfi J, Alduhailan N, et al. Sentiment analysis of Arabic tweets regarding distance learning in Saudi Arabia during the COVID-19 pandemic. Sensors. 2021;21(16):5431. doi: 10.3390/s21165431. - DOI - PMC - PubMed

LinkOut - more resources