Abstract
The whole world is facing health challenges due to wide spread of COVID-19 pandemic. To control the spread of COVID-19, the development of its vaccine is the need of hour. Considering the importance of the vaccines, many industries have put their efforts in vaccine development. The higher immunity against the COVID can be achieved by high intake of the vaccines. Therefore, it is important to analysis the people's behaviour and sentiments towards vaccines. Today is the era of social media, where people mostly share their emotions, experience, or opinions about any trending topic in the form of tweets, comments or posts. In this study, we have used the freely available COVID-19 vaccines dataset and analysed the people reactions on the vaccine campaign using artificial intelligence methods. We used TextBlob() function of python and found out the polarity of the tweets. We applied the BERT model and classify the tweets into negative and positive classes based on their polarity values. The classification results show that BERT has achieved maximum values of precision, recall and F score for both positive and negative sentiment classification.
Keywords: COVID-19, Vaccines campaign, Sentiments monitoring, Vaccine hesitancy, Social media data analysis, AI based modeling
References
- 1.Adamu H., Lutf S.L., Malim N.H.A.H., Hassan R., Di Vaio A., Mohamed A.S.A. Framing twitter public sentiment on Nigerian government COVID-19 palliatives distribution using machine learning. Sustain. 2021;13 doi: 10.3390/su13063497. [DOI] [Google Scholar]
- 2.Ceci M., Corizzo R., Fumarola F., Ianni M., Malerba D., Maria G., Masciari E., Oliverio M., Rashkovska A. In: Proceedings of the 19th International Database Engineering & Applications Symposium. Desai B.C, Toyama M, editors. ACM; Yokohama, Japan: 2015. Big data techniques for supporting accurate predictions of energy production from renewable sources; pp. 62–71.URL July 13-15, 2015. doi:10.1145/2790755.2790762. [DOI] [Google Scholar]
- 3.Chou W.Y.S., Budenz A. Considering Emotion in COVID-19 Vaccine Communication: Addressing Vaccine Hesitancy and Fostering Vaccine Confdence. Health Commun. 2020;35:1718–1722. doi: 10.1080/10410236.2020.1838096. URL doi:10.1080/10410236.2020.1838096. [DOI] [PubMed] [Google Scholar]
- 4.Das S., Dutta A. Characterizing public emotions and sentiments in COVID-19 environment: A case study of India. J. Hum. Behav. Soc. Environ. 2020;31:1–14. doi: 10.1080/10911359.2020.1781015. URL doi:10.1080/10911359.2020.1781015. [DOI] [Google Scholar]
- 5.Flesca S., Furfaro F., Masciari E. On the minimization of xpath queries. J. ACM. 2008;55(2):1–2. doi: 10.1145/1326554.1326556. URL 46. doi:10.1145/1326554.1326556. [DOI] [Google Scholar]
- 6.Flesca S., Masciari E. Efcient and efective web change detection. Data Knowl. Eng. 2003;46:203–224. doi: 10.1016/S0169-023X(02)00210-0. URL doi:10.1016/S0169-023X(02)00210-0. [DOI] [Google Scholar]
- 7.Freed G.L. Actionable lessons for the US COVID vaccine program. Isr. J. Health Policy Res. 2021;10:2–4. doi: 10.1186/s13584-021-00452-2. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 8.Green M.S., Abdullah R., Vered S., Nitzan D. A study of ethnic, gender and educational diferences in attitudes toward COVID-19 vaccines in Israel – implications for vaccination implementation policies. Isr. J. Health Policy Res. 2021;10:1–12. doi: 10.1186/s13584-021-00458-w. doi:10.1186/s13584-021-00458-w. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 9.Manguri H., K. N.Ramadhan, R. R.Mohammed Amin. Twitter Sentiment Analysis on Worldwide COVID-19 Outbreaks. Kurdistan J. Appl. Res. 2020:54–65. doi: 10.24017/covid.8. [DOI] [Google Scholar]
- 10.Hogan C., Atta M., Anderson P., Stead T., Solomon M., Banerjee P., Sleigh B., Shivdat J., Webb McAdams A., Ganti L. Knowledge and attitudes of us adults regarding COVID-19. Int. J. Emerg. Med. 2020;13:1–6. doi: 10.1186/s12245-020-00309-6. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 11.Huang H., Peng Z., Wu H., Xie Q. A big data analysis on the fve dimensions of emergency management information in the early stage of COVID-19 in China. J. Chinese Gov. 2020;5:213–233. doi: 10.1080/23812346.2020.1744923. URL 10.1080/23812346.2020.1744923. [DOI] [Google Scholar]
- 12.Jelodar, H., Wang, Y., Orji, R., Huang, H., 2020. Deep sentiment classifcation and topic discovery on novel coronavirus or COVID-19 online discussions: NLP using LSTM recurrent neural network approach. arXiv 24, 2733–2742. [DOI] [PubMed]
- 13.Kourlaba G., Kourkouni E., Maistreli S., Tsopela C.G., Molocha N.M., Triantafyllou C., Koniordou M., Kopsidas I., Chorianopoulou E., Maroudi-Manta S., Filippou D., Zaoutis T.E. Willingness of Greek general population to get a COVID-19 vaccine. Glob. Heal. Res. Policy. 2021;6:1–10. doi: 10.1186/s41256-021-00188-1. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 14.Lazarus J.V., Ratzan S.C., Palayew A., Gostin L.O., Larson H.J., Rabin K., Kimball S., El-Mohandes A. A global survey of potential acceptance of a COVID-19 vaccine. Nat. Med. 2021;27:225–228. doi: 10.1038/s41591-020-1124-9. URL doi:10.1038/s41591-020-1124-9 http://dx.doi.org/10.1038/s41591-020-1124-9. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 15.Luo Y., Xu X. Comparative study of deep learning models for analyzing online restaurant reviews in the era of the COVID-19 pandemic. Int. J. Hosp. Manag. 2021;94 doi: 10.1016/j.ijhm.2020.102849. URL 10.1016/j.ijhm.2020.102849. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 16.Pota M., Ventura M., Catelli R., Esposito M. An efective bert-based pipeline for twitter sentiment analysis: A case study in Italian. Sensors (Switzerland) 2021;21:1–21. doi: 10.3390/s21010133. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 17.Raheja S., Asthana A. Proc. Confu. 2021 11th Int. Conf. Cloud Comput. Data Sci. Eng; 2021. Sentimental analysis of twitter comments on COVID-19; pp. 704–708. [DOI] [Google Scholar]
- 18.Rustam F., Khalid M., Aslam W., Rupapara V., Mehmood A., Choi G.S. A performance comparison of supervised machine learning models for Covid-19 tweets sentiment analysis. PLoS One. 2021;16:1–23. doi: 10.1371/journal.pone.0245909. URL doi:10.1371/journal.pone.0245909 http://dx.doi.org/10.1371/journal.pone.0245909. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 19.Samuel J., Rahman M.M., Ali G.G.N., Samuel Y., Pelaez A., Chong P.H.J., Yakubov M. Feeling Positive about Reopening? New Normal Scenarios from COVID-19 US Reopen Sentiment Analytics. IEEE Access. 2020;8:142173–142190. doi: 10.1109/ACCESS.2020.3013933. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 20.Seale H., Heywood A.E., Leask J., Sheel M., Durrheim D.N., Bolsewicz K., Kaur R. Examining Australian public perceptions and behaviors towards a future COVID-19 vaccine. medRxiv. 2020:1–9. doi: 10.1101/2020.09.29.20204396. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 21.Sv, P., Ittamalla, R., Deepak, G., 2020. Analyzing the attitude of Indian citizens towards COVID-19 vaccine e A text analytics study . [DOI] [PMC free article] [PubMed]
- 22.Umair A., Masciari E. Sentimental and spatial analysis of covid-19 vaccines tweets. Journal of Intelligent Information Systems. 2022:1–21. doi: 10.1007/s10844-022-00699-4. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 23.Umair A., Masciari E., Habib Ullah M.H. 25th International Database Engineering & Applications Symposium. Association for Computing Machinery; New York, NY, USA: 2021. Sentimental analysis applications and approaches during covid-19: A survey; pp. 304–308.URL 10.1145/3472163.3472274. [DOI] [Google Scholar]
- 24.Yadav N., Singh A.K. ACM Int. Conf. Proceeding Ser. 2020. Bi-directional Encoder Representation of Transformer model for Sequential Music Recommender System; pp. 49–53. [DOI] [Google Scholar]
- 25.Zhou B., Cheng C., Ma G., Zhang Y. Remaining Useful Life Prediction of Lithium-ion Battery based on Attention Mechanism with Positional Encoding. IOP Conf. Ser. Mater. Sci. Eng. 2020;895:0–9. doi: 10.1088/1757-899X/895/1/012006. [DOI] [Google Scholar]