Utilizing AI for extracting insights on post WHO's COVID-19 vaccination declaration from X (Twitter) social network

Ali S. Abed Al Sailawi; Mohammad Reza Kangavari; Ali S. Abed Al Sailawi; Mohammad Reza Kangavari

doi:10.3934/publichealth.2024018

AIMS Public Health

2024, Volume 11, Issue 2: 349-378. doi: 10.3934/publichealth.2024018

Previous Article Next Article

Technical note

Utilizing AI for extracting insights on post WHO's COVID-19 vaccination declaration from X (Twitter) social network

Ali S. Abed Al Sailawi ^{1,2
,
,},
Mohammad Reza Kangavari ^{1
,
,}

1.
School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran
2.
College of Law, University of Misan, Amarah, Iraq

Received: 11 January 2024 Revised: 27 February 2024 Accepted: 12 March 2024 Published: 18 March 2024

This study explores the use of artificial intelligence (AI) to analyze information from X (previously Twitter) feeds related to COVID-19, specifically focusing on the time following the World Health Organization's (WHO) vaccination announcement. This aspect of the pandemic has not been studied by other researchers focusing on vaccination news. By utilizing advanced AI algorithms, the research aims to examine a wealth of data, sentiments, and trends to enhance crisis management strategies effectively. Our methods involved collecting a dataset of tweets from December 2020 to July 2021. By using specific keywords strategically, we gathered a substantial 15.5 million tweets, focusing on important hashtags like #vaccine and #coronavirus while filtering out irrelevant replies and retweets. The assessment of three different machine learning models–BiLSTM, FFNN, and CNN – highlights the exceptional performance of BiLSTM, achieving an impressive F1-score of 0.84 on the test set, with Precision and Recall metrics at 0.85 and 0.83, respectively. The study provides a detailed visualization of global sentiments on COVID-19 topics, with a main goal of extracting insights to manage public health crises effectively. Sentiment labels were predicted using various classification models and categorized as positive, negative, and neutral for each country after adjusting for population differences. An important finding from the analysis is the variation in sentiments across regions, for instance, with Eastern European countries showing positive views on post-vaccination economic recovery, while China and the United States express negative opinions on the same topic.
- AI,
- Twitter feeds,
- COVID-19,
- crisis response,
- WHO,
- vaccination,
- decision support system,
- public sentiment,
- real-time data analysis
Citation: Ali S. Abed Al Sailawi, Mohammad Reza Kangavari. Utilizing AI for extracting insights on post WHO's COVID-19 vaccination declaration from X (Twitter) social network[J]. AIMS Public Health, 2024, 11(2): 349-378. doi: 10.3934/publichealth.2024018

Related Papers:

Abstract

This study explores the use of artificial intelligence (AI) to analyze information from X (previously Twitter) feeds related to COVID-19, specifically focusing on the time following the World Health Organization's (WHO) vaccination announcement. This aspect of the pandemic has not been studied by other researchers focusing on vaccination news. By utilizing advanced AI algorithms, the research aims to examine a wealth of data, sentiments, and trends to enhance crisis management strategies effectively. Our methods involved collecting a dataset of tweets from December 2020 to July 2021. By using specific keywords strategically, we gathered a substantial 15.5 million tweets, focusing on important hashtags like #vaccine and #coronavirus while filtering out irrelevant replies and retweets. The assessment of three different machine learning models–BiLSTM, FFNN, and CNN – highlights the exceptional performance of BiLSTM, achieving an impressive F1-score of 0.84 on the test set, with Precision and Recall metrics at 0.85 and 0.83, respectively. The study provides a detailed visualization of global sentiments on COVID-19 topics, with a main goal of extracting insights to manage public health crises effectively. Sentiment labels were predicted using various classification models and categorized as positive, negative, and neutral for each country after adjusting for population differences. An important finding from the analysis is the variation in sentiments across regions, for instance, with Eastern European countries showing positive views on post-vaccination economic recovery, while China and the United States express negative opinions on the same topic.

Acknowledgments

We extend our gratitude to the faulty members for their assistance in providing the supplementary data on the survey. We also appreciate their valuable contributions to the discussions related to this study.

Conflicts of Interest

The authors declare no conflict of interest.

References

[1]	Band S S, Yarahmadi A, Hsu C C, et al. (2023) Application of explainable artificial intelligence in medical health: A systematic review of interpretability methods. Inform Med Unlocked 2023: 101286. https://doi.org/10.1016/j.imu.2023.101286
[2]	Caroprese L, Comito C, Zumpano E Fake news on social media: Current research and future directions. In International Conference on Pervasive Knowledge and Collective Intelligence on Web and social media. Cham: Springer Nature Switzerland: p. 57-64. https://doi.org/10.1007/978-3-031-31469-8_4
[3]	Comito C, Caroprese L, Zumpano E (2023) Multimodal fake news detection on social media: A survey of deep learning techniques. Soc Netw Anal Min 13: 101. https://doi.org/10.1007/s13278-023-01104-w
[4]	Wankhade M, Rao A C S, Kulkarni C (2022) A survey on sentiment analysis methods, applications, and challenges. Artif Intell Rev 55: 5731-5780. https://doi.org/10.1007/s10462-022-10144-1
[5]	Rezaei N, Jafari M, Nazari A, et al. (2020) A novel methodology and new concept of SARS-CoV-2 elimination in heating and ventilating air conditioning systems using waste heat recovery. AIP Adv 10: 085308. https://doi.org/10.1063/5.0021575
[6]	Chaufan C, Manwell L, Gabbay B, et al. (2023) Appraising the decision-making process concerning COVID-19 policy in postsecondary education in Canada: A critical scoping review protocol. AIMS Public Health 10: 918-933. https://doi.org/10.3934/publichealth.2023059
[7]	Tomic K (2023) The Impact of the Covid-19 Pandemic on the Sports Industry and Sports Insurance: Case of Novak Djokovic and Australian Open Tennis Tournament 2022. In Covid-19 and Insurance. Cham: Springer International Publishing: p. 301-320. https://doi.org/10.1007/978-3-031-13753-2_11
[8]	Xue J, Chen J, Chen C, et al. (2020) Public discourse and sentiment during the COVID 19 pandemic: Using Latent Dirichlet Allocation for topic modeling on Twitter. PloS One 15: e0239441. https://doi.org/10.1371/journal.pone.0239441
[9]	Xue J, Chen J, Hu R, et al. (2020) Twitter discussions and emotions about the COVID-19 pandemic: Machine learning approach. J Med Internet Res 22: e20550. https://doi.org/10.2196/20550
[10]	Hung M, Lauren E, Hon E S, et al. (2020) Social network analysis of COVID-19 sentiments: Application of artificial intelligence. J Med Internet Res 22: e22590. https://doi.org/10.2196/22590
[11]	Imran A S, Daudpota S M, Kastrati Z, et al. (2020) Cross-cultural polarity and emotion detection using sentiment analysis and deep learning on COVID-19 related tweets. IEEE Access 8: 181074-181090. https://doi.org/10.1109/ACCESS.2020.3027350
[12]	Chandrasekaran R, Mehta V, Valkunde T, et al. (2020) Topics, trends, and sentiments of tweets about the COVID-19 pandemic: Temporal infoveillance study. J Med Internet Res 22: e22624. https://doi.org/10.2196/22624
[13]	Yin H, Yang S, Li J Detecting topic and sentiment dynamics due to COVID-19 pandemic using social media. In Advanced Data Mining and Applications: 16th International Conference, ADMA 2020, Foshan, China, November 12–14, 2020.Springer International Publishing: p. 610-623. https://doi.org/10.1007/978-3-030-65390-3_46
[14]	Abd-Alrazaq A, Alhuwail D, Househ M, et al. (2020) Top concerns of tweeters during the COVID-19 pandemic: infoveillance study. J Med Internet Res 22: e19016. https://doi.org/10.2196/19016
[15]	Aljabri M, Chrouf S M B, Alzahrani N A, et al. (2021) Sentiment analysis of Arabic tweets regarding distance learning in Saudi Arabia during the COVID-19 pandemic. Sensors (Basel) 21: 5431. https://doi.org/10.3390/s21165431
[16]	Alqurashi S, Hamoui B, Alashaikh A, et al. (2021) Eating garlic prevents COVID-19 infection: Detecting misinformation on the Arabic content of Twitter. arXiv preprint arXiv 2021: 2101.05626.
[17]	Ameur M S H, Aliane H (2021) AraCOVID19-MFH: Arabic COVID-19 multi-label fake news & hate speech detection dataset. Procedia Computer Sci 189: 232-241. https://doi.org/10.1016/j.procs.2021.05.086
[18]	Ameur M S H, Aliane H (2021) Aracovid19-ssd: Arabic covid-19 sentiment and sarcasm detection dataset. arXiv preprint arXiv 2021: 2110.01948.
[19]	Alsudias L, Rayson P (2020) COVID-19 and Arabic Twitter: How can Arab world governments and public health organizations learn from social media?. In Proceedings of the 1st Workshop on NLP for COVID-19 at ACL 2020 c2020.
[20]	Pedrosa A L, Bitencourt L, Fróes A C F, et al. (2020) Emotional, behavioral, and psychological impact of the COVID-19 pandemic. Front Psychol 11: 566212. https://doi.org/10.3389/fpsyg.2020.566212
[21]	Fernandes N (2020) Economic effects of coronavirus outbreak (COVID-19) on the world economy. IESE Business School Working Paper No . WP-1240-E. https://doi.org/10.2139/ssrn.3557504
[22]	Polyzos E, Fotiadis A, Huan T C (2023) From Heroes to Scoundrels: Exploring the effects of online campaigns celebrating frontline workers on COVID-19 outcomes. Technol Soc 72: 102198. https://doi.org/10.1016/j.techsoc.2023.102198
[23]	Mittelmeier J, Cockayne H (2023) Global representations of international students in a time of crisis: A qualitative analysis of Twitter data during COVID-19. Int Stud Sociol Educ 32: 487-510. https://doi.org/10.1080/09620214.2022.2042357
[24]	Chen J, Becken S, Stantic B (2023) Travel bubbles to maintain safe space for international travel during crisis–emotions reflected in twitter posts. Curr Issues Tour 26: 2479-2493. https://doi.org/10.1080/13683500.2022.2089546
[25]	Carvache-Franco O, Carvache-Franco M, Carvache-Franco W, et al. (2023) Topic and sentiment analysis of crisis communications about the COVID-19 pandemic in Twitter's tourism hashtags. Tour Hosp Res 23: 44-59. https://doi.org/10.1177/14673584221085470
[26]	Regalado-Pezúa O, Carvache-Franco O, Carvache-Franco M, et al. (2023) Effect of negative emotions in consumption during the COVID-19 pandemic: A study from Peru. Plos One 18: e0293932. https://doi.org/10.1371/journal.pone.0293932
[27]	Polyzos E (2023) Inflation and the war in Ukraine: Evidence using impulse response functions on economic indicators and Twitter sentiment. Res Int Bus Financ 66: 102044. https://doi.org/10.1016/j.ribaf.2023.102044
[28]	Mandal R, Chen J, Becken S, et al. (2023) Tweets topic classification and sentiment analysis based on transformer-based language models. Vietnam J Comput Sci 10: 117-134. https://doi.org/10.1142/S2196888822500269
[29]	Yousefinaghani S, Dara R, Mubareka S, et al. (2021) An analysis of COVID-19 vaccine sentiments and opinions on Twitter. Int J Infec Dis 108: 256-262. https://doi.org/10.1016/j.ijid.2021.05.059
[30]	Hayawi K, Shahriar S, Serhani M A, et al. (2022) ANTi-Vax: A novel Twitter dataset for COVID-19 vaccine misinformation detection. Public Health 203: 23-30. https://doi.org/10.1016/j.puhe.2021.11.022
[31]	Bonifazi G, Breve B, Cirillo S, et al. (2022) Investigating the COVID-19 vaccine discussions on Twitter through a multilayer network-based approach. Inf Process Manag 59: 103095. https://doi.org/10.1016/j.ipm.2022.103095
[32]	Kim S, Park H, Lee J (2020) Word2vec-based latent semantic analysis (W2V-LSA) for topic modeling: A study on blockchain technology trend analysis. Expert Syst Appl 152: 113401. https://doi.org/10.1016/j.eswa.2020.113401
[33]	Yu D, Xiang B (2023) Discovering topics and trends in the field of Artificial Intelligence: Using LDA topic modeling. Expert Syst Appl 2023: 120114. https://doi.org/10.1016/j.eswa.2023.120114
[34]	Hussain S, Ayoub M, Yu Y, et al. (2023) Ensemble deep learning framework for situational aspects-based annotation and classification of international student's Tweets during COVID-19. Comput Mater Con 75: 5355-5377. https://doi.org/10.32604/cmc.2023.036779
[35]	Nurdin N, Kluza K, Fitria M, et al. Analysis of social media data using deep learning and NLP method for potential use as natural disaster management in Indonesia. In 2023 2nd International Conference on Computer System, Information Technology, and Electrical Engineering (COSITE); IEEE c2023: p. 143-148. https://doi.org/10.1109/COSITE60233.2023.10249849
[36]	Mutanga M B, Abayomi A (2022) Tweeting on COVID-19 pandemic in South Africa: LDA-based topic modelling approach. Afr J Sci Technol In 14: 163-172. https://doi.org/10.1080/20421338.2020.1817262
[37]	Al Sailawi Ali S. Abed, Kangavari Mohammad Reza (2024) Analyzing social media data to understand long-term crisis management challenges of COVID-19. J Fusion: Pract Appl 14: 227-243. https://doi.org/10.54216/FPA.140219
[38]	Wang X, Wei F, Liu X, et al. (2011) Topic sentiment analysis in twitter: a graph-based hashtag sentiment classification approach. In Proceedings of the 20th ACM international conference on Information and knowledge management c2011: p. 1031-1040. https://doi.org/10.1145/2063576.2063726
[39]	Karami A, Shah V, Vaezi R, et al. (2020) Twitter speaks: A case of national disaster situational awareness. J Inform Sci 46: 313-324. https://doi.org/10.1177/0165551519828620
[40]	Gupta I, Joshi N (2021) Real-time twitter corpus labelling using automatic clustering approach. Int J Comput Digit Syst 10: 519-532. https://doi.org/10.12785/ijcds/100150
[41]	Abdul-Mageed M, Elmadany A, Nagoudi E M B, et al. (2020) Mega-COV: A billion-scale dataset of 100+ languages for COVID-19. arXiv preprint arXiv 2020: 2005.06012. https://doi.org/10.18653/v1/2021.eacl-main.298
[42]	Basiri M E, Nemati S, Abdar M, et al. (2021) A novel fusion-based deep learning model for sentiment analysis of COVID-19 tweets. Knowl Based Syst 228: 107242. https://doi.org/10.1016/j.knosys.2021.107242
[43]	Tripathi M (2021) Sentiment analysis of nepali covid19 tweets using nb svm and lstm. J Artif Intell 3: 151-168. https://doi.org/10.36548/jaicn.2021.3.001
[44]	Cevallos M, De Biase M, Vocaturo E, et al. (2022) Fake news detection on COVID 19 tweets via supervised learning approach. In 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM); IEEE c2022: p. 2765-2772. https://doi.org/10.1109/BIBM55620.2022.9994918
[45]	Venkatesh S, Gill A, Kim L, et al. (2023) Mothers' intentions to vaccinate their children for COVID-19. AIMS Public Health 10: 209-218. https://doi.org/10.3934/publichealth.2023016
[46]	Andryukov B G, Besednova N N (2021) Older adults: Panoramic view on the COVID-19 vaccination. AIMS Public Health 8: 388-415. https://doi.org/10.3934/publichealth.2021030
[47]	Bulut O, Poth C N (2022) Rapid assessment of communication consistency: sentiment analysis of public health briefings during the COVID-19 pandemic. AIMS Public Health 9: 293-306. https://doi.org/10.3934/publichealth.2022020
[48]	Walmsley T, Rose A, Wei D (2021) The Impacts of the Coronavirus on the Economy of the United States. Econ Disaster Clim Chang 5: 1-52. https://doi.org/10.1007/s41885-020-00080-1
[49]	CEPAL N Impact of COVID-19 on the United States economy and the policy response (2020). Available from: https://hdl.handle.net/11362/45984

Reader Comments

Your name:*

Email:*
© 2024 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)