COVID-19 Vaccines Related User’s Response Categorization: History
View Latest Version
Please note this is an old version of this entry, which may differ significantly from the current revision.
Contributor:
Ahmed Shahzad
,
Bushra Zafar
,
Nouman Ali
,
Uzma Jamil
,
Abdulaziz Jarallah Alghadhban
,
Muhammad Assam
,
Nivin A. Ghamry
,
Elsayed Tag Eldin

Respiratory viruses known as coronaviruses infect people and cause death. The multiple crown-like spikes on the virus’s surface give them the name “corona”. The pandemic has resulted in a global health crisis and it is expected that every year people will have to fight against different COVID-19 variants. In this critical situation, the existence of COVID-19 vaccinations provides hope for mankind. Despite severe vaccination campaigns and recommendations from health experts and the government, people have perceptions regarding vaccination risks and share their views and experiences on social media platforms. Social attitudes to these types of vaccinations are influenced by their positive and negative effects. The analysis of such opinions can help to determine social trends and formulate policies to increase vaccination acceptance. 

  • COVID-19
  • vaccines
  • Twitter
  • sentiment analysis
  • classification
  • machine learning

1. Introduction

Machine learning and deep learning models are used in various real-time domains such as industrial automation, design of design support systems for medical domains and multimedia analysis [1][2][3][4][5]. Pandemics occur and lead to extensive morbidity and mortality worldwide. In December of 2019, a case of pneumonia of unknown origin was reported in Wuhan, China. From there, the epidemic of the coronavirus swiftly spread to other countries [6][7][8][9][10], leading to the widespread outbreak of COVID-19 on the mainland. The severe acute respiratory syndrome coronavirus is causing a pandemic of coronavirus disease 2019 (COVID-19) all over the globe, and China is one of the countries affected (SARS-COV-2). China was the first country to have an outbreak of the disease. It was also the first country to respond with harsh measures, such as lockdowns and rules about wearing face masks. China was also one of the first countries to get the outbreak under control. The coronavirus (COVID-19) viruses have made their way to many parts of the world. This virus has a high rate of spread and is harmful to humans [11].
Italy was the first European country to experience a significant COVID-19 outbreak, with the detection of the first case on the 21 February 2020 in the province of Lodi in the region of Lombardy. While each province in Italy had confirmed cases of the virus by mid-March 2020, the diffusion of the outbreak in the country was very heterogeneous. The majority of cases were concentrated in Lombardy in the north of the country [12][13].
The World Health Organization (WHO) called the COVID-19 outbreak the sixth public health emergency of international concern (PHEIC) on 30 January 2020. On 11 March 2020, the WHO said that COVID-19 had become a pandemic [14]. This year’s new coronavirus killed 85,522 people on 9 April 2020, and the case fatality rate (CFR) was 5.95%. COVID-19 has been classified by the WHO as having a very high global risk. Because lockdowns have been implemented in so many areas, the pandemic scenario has impacted virtually every aspect of society, including the economy [15][16]. Coronavirus disease (COVID-19) is a pandemic and an issue that exists in more than 200 nations throughout the world. Many countries have been badly affected by COVID-19 and lots of people have died in the last two years [16]. The high volume of international travel was the primary factor in the disease’s dissemination around the globe; the presence of local contagious links played a secondary role. For example, in 2018, more than 4 billion individuals, or almost six out of every ten persons on the planet, traveled worldwide by means of commercial airplanes [17].
In response to the unusual spread of the illness, there have been concerted attempts on a worldwide scale to collaborate on combating the pandemic. The creation of a vaccine is one of the potential strategies that may be used to combat the COVID-19 pandemic. A chemical that stimulates the development of adaptive immunity in the body and hence assists in the body’s fight against various illnesses and diseases is known as a vaccine [17][18][19]. Many organizations have developed vaccines to avoid and overcome this situation. People have to vaccinate themselves to reduce the threat of this malignant disease [20]. For this, they need some opinion about different types of vaccines available in the market to select the most suitable vaccine for themselves. Social media platforms such as Twitter have proved to be a valuable resource that provides instantaneous access for information tracking and evaluation. In pandemic times, Twitter has been used in various studies as a source of information, e.g., back in 2009 during the HINI outbreak [21]. Twitter has been widely used in various studies for the identification of user’s concerns, misinformation spread and sentiment analysis [22]. Twitter users have expressed their opinions regarding COVID-19 vaccination.

2. COVID-19 Vaccines Related User’s Response Categorization

This section presents the recent literature on the COVID-19 pandemic which emphasizes the importance of effective vaccination for the whole population.
Machine learning and neural networks have applications in difference domains such as aerial image classification [23][24][25][26], face recognition [27], Internet of Things [28][29], healthcare [30][31][32] and sentiment analysis, etc. Manguri et al. [33] stated that the rise of social data on the internet has accelerated. This leads to study in order to obtain access to the data and information for a variety of academic and commercial purposes. The global COVID-19 sickness has now expanded internationally, and social data on the web includes numerous real-life incidents that happened in everyday life. Many people, including media outlets and government institutions, are disseminating the newest information and viewpoints on the coronavirus. The Twitter data was crawled from Twitter social media through a python programming language, and sentiment analysis was performed using the text blob library in python. The evaluation results of sentiment analysis are shown as a graphical representation based on the data. The information originated from Twitter, where it was discovered via the use of a search for two distinct hashtag keywords: (COVID-19 and coronavirus). In another study [34], the authors argued that a global infrastructure to enable both normal and pandemic/epidemic adult vaccination is urgently needed because of the global connections. Since the number of older persons is continually increasing, the need for a framework to propose vaccinations and establish strong platforms to distribute them was obvious. For older individuals, their families, communities, and nations, adult vaccination as a policy has the potential to protect and improve medical, social, and economic results. COVID-19 vaccinations will soon be available, but it is important to remember that currently, a number of vaccines are available that can keep adults healthy.
Meena et al. [35] pointed out that social media talks about healthcare were an excellent starting point for assessing people’s feelings. COVID-19 vaccination was the primary hope of practically every human being on Earth. Many people took to Twitter to express their feelings in response to Russia’s first vaccination announcement. Data from tweets were analyzed for the emotions and psychology of the people and the issue of interest they were discussing. The social emotions were disclosed and displayed using computational approaches and algorithms, such as machine-learned and LDA. Sentiment analysis is a technique for recognizing and categorizing views or feelings represented in the source material. A vast amount of data that is rich in sentiment is generated by various types of social media, such as tweets, status updates, blog posts, and so on. The application of sentiment analysis to this user-generated data may be highly helpful in identifying the perspective of the general population. Because of the existence of slang phrases and misspellings, Twitter sentiment analysis is more complex than conventional sentiment analysis. On Twitter, the maximum number of characters permitted is 140. According to authors, there are two methodologies that are employed for interpreting the sentiment gleaned from the text. These are the knowledge-based approach. Alliheibi [36], mentioned that individuals in Saudi Arabia who had received the COVID-19 vaccination were studied via their tweets. People’s replies were classified using computational lexical-semantic approaches. The findings show that the majority of Saudi Arabians have an unfavorable view of the government’s COVID-19 immunization take-up campaign. According to the findings, the use of data mining applications in government institutions and departments can identify trends that could have an adverse impact on policies and practices, as well as help government institutions make appropriate decisions and adopt reliable and workable policies and procedures.
Yousefinaghani et al. [37] pointed out that COVID-19 vaccinations are the subject of an estimated 4.5 million tweets being analyzed in their investigation. It is possible that Twitter, as it was in the study, may be an effective tool for promoting public health by increasing vaccination uptake and decreasing vaccine resistance. Public health officials might benefit from better knowing vaccine feelings and opinions in order to amplify good postings with supportive language and debunk negative ones with confrontational language that spreads misinformation. Public health organizations may also be able to use Twitter and other media to raise positive messaging and actively minimize negative and opposing messages.
Ezhilan et al. [38] performed a study using a convolutional neural network and a recurrent neural network built for sentiment analysis based on text data related to Twitter data sentiment analysis. CNN and RNN sentiment classifiers performed better than other sentiment classifiers, such as SVM, logistic regression, and Nave Bayes, in terms of accuracy and recall, according to the empirical assessment in the study. Also shown in the study was the performance of general-purpose emotion analyzers such as text blob and Vader. Understanding public opinions regarding coronavirus and COVID-19 helps to detect the rise in dread sentiment and unpleasant feelings, which were important for developing much-needed remedies to stop the rapid spread of the pandemic. The use of exploratory and descriptive text analytics and data visualization methodologies helps to uncover the most basic of ideas. Andrzejczak-Grzadko et al. [39] observed that the Vaccine side effects are widespread, although individuals respond to immunizations in various ways. Manufacturers give a list of their goods’ adverse effects. Adverse responses indicate that immunizations are effective and that the immune system is reacting. It compares the AstraZeneca and Pfizer vaccines’ side effects. These responses were more prevalent after the first dosage of the AstraZeneca vaccination than after the first and second doses of the Pfizer vaccine, although they were less common after the Pfizer formulation. The survey was made available on the internet. It was performed on patients who had been immunized with Pfizer or AstraZeneca vaccines. The participants were questioned about adverse effects such as injection site discomfort, arm pain, muscle pain, headache, fever, chills, and exhaustion after receiving the first and second doses of the vaccinations. A total of 705 persons responded to the survey. Pfizer had vaccinated 196 of them, whereas AstraZeneca had immunized 509. A total of 96.5% of those who received the first dose of the AstraZeneca vaccine had at least one post-vaccination response. All of the adverse effects mentioned in the survey were reported by 17.1% of respondents. Vaccine responses were recorded by 93.9% of those who received the first Pfizer dosage, while just 2% of those who received the second dose suffered all of the adverse events listed in the survey. Most of the subjects had post-vaccinal reactions after the second dose of the Pfizer vaccine: 54.8% had more adverse reactions, and 15.8% had fewer adverse reactions than after the first dose, and 29.4% had the same side effects after the first and second doses of the Pfizer vaccine.
Saeed et al. [40] stated that some people were reluctant to get their children vaccinated because they were afraid of the unknown. The first and second post-vaccination side effects of the Sinopharm COVID-19 vaccine were shown to be common and moderate, predictable, non-serious, and not life-threatening. For the first time, the Sinopharm vaccine’s adverse effects have been evaluated among an age group, and the findings might help lessen public vaccination skepticism. Dubey [41] performed a study to explain. In India, the campaign to prevent COVID-19 began on 16 January 2021. Oxford-Covishield AstraZeneca’s and Bharat Biotech’s Covaxin were two vaccines employed in this campaign. This initiative has already surpassed 600,000 people in its first four days, and the government has declared that it would be increased in the following days to secure residents’ immunity. However, there is still a segment of the population that is skeptical about the COVID-19 vaccine. It was carried out to examine the emotions expressed in India’s tweets about these two vaccinations. While the majority of the public has favorable feelings about these vaccinations, the study indicates that there are also negative feelings about them, which are linked to emotions such as fear and wrath. Dumre et al. [42] performed a statistical and sentiment analysis and observed that people in India have begun developing opinions towards them as a result of the impending availability of a vaccine against COVID-19. An investigation of the attitudes and viewpoints of individuals with respect to vaccinations. Out of 200 participants, 32 doctors and 35 participants were vaccinated. The main objectives were to analyze the response to the survey and draw conclusions with the help of data analysis techniques and performed sentiment analysis on participants’ responses to identify what stops people from getting vaccinated.
Cotfas et al. [43] described that machine learning-based posture detection was used to analyze the one-month time between the initial announcement of a coronavirus vaccine and the first real immunization procedure outside of the limited clinical trials. The best classifier was selected after a thorough evaluation of the performance of a number of different conventional and deep learning methods. The suggested method was able to classify the tweets into three primary categories, namely in favor, against, and neutral, with an accuracy of 78.94%. The authors in [44] analyzed that the tweets were categorized into four different emotions based on their content: fear, sadness, rage, and joy. A pleasant environment was produced in the healthcare authorities by using phrases such as “thank you”, “well”, and “good” instead of terms that instill dread in the minds of those who hear them. In light of these findings, local governments have been pushed to impose fact-checkers on social media to combat misleading propaganda. There has been a lack of research on how to verify and categorize tweets, which has led to a rise in the spread of false information. As a result, the authors used Bert, a unique deep-learning model, to obtain better classification accuracy in comparison to standard models of ML. Bert’s 89% accuracy outperformed other models including LR, SVM, and LSTM, according to the results. The research results helped to clarify public opinion on pandemics and provided a guideline to medical authorities, public, and private sector employees to overcome unnecessary concern during pandemics.

This entry is adapted from the peer-reviewed paper 10.3390/computation10080141

References

  1. Khalil, T.; Akram, M.U.; Khalid, S.; Dar, S.H.; Ali, N. A study to identify limitations of existing automated systems to detect glaucoma at initial and curable stage. Int. J. Imaging Syst. Technol. 2021, 31, 1155–1173.
  2. Aslam, M.A.; Salik, M.N.; Chughtai, F.; Ali, N.; Dar, S.H.; Khalil, T. Image classification based on mid-level feature fusion. In Proceedings of the 2019 15th International Conference on Emerging Technologies (ICET) IEEE, Peshawar, Pakistan, 2–3 December 2019; pp. 1–6.
  3. Rasheed, A.; Zafar, B.; Rasheed, A.; Ali, N.; Sajid, M.; Dar, S.H.; Habib, U.; Shehryar, T.; Mahmood, M.T. Fabric defect detection using computer vision techniques: A comprehensive review. Math. Probl. Eng. 2020, 2020, 8189403.
  4. Riaz, F.; Jabbar, S.; Sajid, M.; Ahmad, M.; Naseer, K.; Ali, N. A collision avoidance scheme for autonomous vehicles inspired by human social norms. Comput. Electr. Eng. 2018, 69, 690–704.
  5. Ali, N.; Bajwa, K.B.; Sablatnig, R.; Chatzichristofis, S.A.; Iqbal, Z.; Rashid, M.; Habib, H.A. A novel image retrieval based on visual words integration of SIFT and SURF. PLoS ONE 2016, 11, e0157428.
  6. Wang, S.; Xu, H.; Kotian, R.P.; D’souza, B.; Rao, S.S. A study on psychological implications of COVID-19 on nursing professionals. Int. J. Healthc. Manag. 2021, 14, 300–305.
  7. Ceylan, Z. Estimation of COVID-19 prevalence in Italy, Spain, and France. Sci. Total Environ. 2020, 729, 138817.
  8. Wang, L.; Li, J.; Guo, S.; Xie, N.; Yao, L.; Cao, Y.; Day, S.W.; Howard, S.C.; Graff, J.C.; Gu, T.; et al. Real-time estimation and prediction of mortality caused by COVID-19 with patient information based algorithm. Sci. Total Environ. 2020, 727, 138394.
  9. Zhu, N.; Zhang, D.; Wang, W.; Li, X.; Yang, B.; Song, J.; Zhao, X.; Huang, B.; Shi, W.; Lu, R.; et al. A novel coronavirus from patients with pneumonia in China, 2019. N. Engl. J. Med. 2020, 382, 727–733.
  10. Du Toit, A. Outbreak of a novel coronavirus. Nat. Rev. Microbiol. 2020, 18, 123.
  11. Nurdeni, D.A.; Budi, I.; Santoso, A.B. Sentiment analysis on COVID-19 vaccines in Indonesia: From the perspective of Sinovac and Pfizer. In Proceedings of the 2021 3rd East Indonesia Conference on Computer and Information Technology (EIConCIT) IEEE, Surabaya, Indonesia, 9–11 April 2021; pp. 122–127.
  12. Odone, A.; Delmonte, D.; Scognamiglio, T.; Signorelli, C. COVID-19 deaths in Lombardy, Italy: Data in context. Lancet Public Health 2020, 5, e310.
  13. Battiston, P.; Kashyap, R.; Rotondi, V. Reliance on scientists and experts during an epidemic: Evidence from the COVID-19 outbreak in Italy. SSM-Popul. Health 2021, 13, 100721.
  14. Gomes, G. Naming the coronavirus disease (COVID-19) and the virus that causes it. Braz. J. Implantol. Health Sci. 2020, 2, 1–3.
  15. Abid, K.; Bari, Y.A.; Younas, M.; Tahir Javaid, S.; Imran, A. Progress of COVID-19 Epidemic in Pakistan. Asia Pac. J. Public Health 2020, 32, 154–156.
  16. Setiati, S.; Azwar, M.K. COVID-19 and Indonesia. Acta Med. Indones. 2020, 52, 84–89.
  17. Reshi, A.A.; Rustam, F.; Aljedaani, W.; Shafi, S.; Alhossan, A.; Alrabiah, Z.; Ahmad, A.; Alsuwailem, H.; Almangour, T.A.; Alshammari, M.A.; et al. COVID-19 Vaccination-Related Sentiments Analysis: A Case Study Using Worldwide Twitter Dataset. Healthcare 2022, 10, 411.
  18. Hung, I.F.; Poland, G.A. Single-dose Oxford–AstraZeneca COVID-19 vaccine followed by a 12-week booster. Lancet 2021, 397, 854–855.
  19. Chagla, Z. The BNT162b2 (BioNTech/Pfizer) vaccine had 95% efficacy against COVID-19 7 days after the 2nd dose. Ann. Intern. Med. 2021, 174, JC15.
  20. Bono, S.A.; Siau, C.S.; Chen, W.S.; Low, W.Y.; Faria de Moura Villela, E.; Pengpid, S.; Hasan, M.T.; Sessou, P.; Ditekemena, J.D.; Amodan, B.O.; et al. Adults’ acceptance of COVID-19 vaccine for children in selected lower-and middle-income countries. Vaccines 2021, 10, 11.
  21. Marcec, R.; Likic, R. Using twitter for sentiment analysis towards AstraZeneca/Oxford, Pfizer/BioNTech and Moderna COVID-19 vaccines. Postgrad. Med. J. 2021, 98, 544–550.
  22. Chew, C.; Eysenbach, G. Pandemics in the age of Twitter: Content analysis of Tweets during the 2009 H1N1 outbreak. PLoS ONE 2010, 5, e14118.
  23. Ali, N.; Zafar, B.; Iqbal, M.K.; Sajid, M.; Younis, M.Y.; Dar, S.H.; Mahmood, M.T.; Lee, I.H. Modeling global geometric spatial information for rotation invariant classification of satellite images. PLoS ONE 2019, 14, e0219833.
  24. Tufail, A.B.; Ullah, I.; Khan, R.; Ali, L.; Yousaf, A.; Rehman, A.U.; Alhakami, W.; Hamam, H.; Cheikhrouhou, O.; Ma, Y.K. Recognition of Ziziphus lotus through Aerial Imaging and Deep Transfer Learning Approach. Mob. Inf. Syst. 2021, 2021, 4310321.
  25. Zafar, B.; Ashraf, R.; Ali, N.; Iqbal, M.K.; Sajid, M.; Dar, S.H.; Ratyal, N.I. A novel discriminating and relative global spatial image representation with applications in CBIR. Appl. Sci. 2018, 8, 2242.
  26. Ali, N.; Bajwa, K.B.; Sablatnig, R.; Mehmood, Z. Image retrieval by addition of spatial information based on histograms of triangular regions. Comput. Electr. Eng. 2016, 54, 539–550.
  27. Sajid, M.; Ali, N.; Dar, S.H.; Zafar, B.; Iqbal, M.K. Short search space and synthesized-reference re-ranking for face image retrieval. Appl. Soft Comput. 2021, 99, 106871.
  28. Asif, M.; Khan, W.U.; Afzal, H.; Nebhen, J.; Ullah, I.; Rehman, A.U.; Kaabar, M.K. Reduced-complexity LDPC decoding for next-generation IoT networks. Wirel. Commun. Mob. Comput. 2021, 2021, 2029560.
  29. Fatima, S.; Aslam, N.A.; Tariq, I.; Ali, N. Home security and automation based on internet of things: A comprehensive review. In Proceedings of the IOP Conference Series: Materials Science and Engineering, Topi, Pakistan, 9–10 June 2020; IOP Publishing: Bristl, UK, 2020; Volume 899, p. 012011.
  30. Tufail, A.B.; Ullah, I.; Khan, W.U.; Asif, M.; Ahmad, I.; Ma, Y.K.; Khan, R.; Ali, M. Diagnosis of diabetic retinopathy through retinal fundus images and 3D convolutional neural networks with limited number of samples. Wirel. Commun. Mob. Comput. 2021, 2021, 6013448.
  31. Shabbir, A.; Rasheed, A.; Shehraz, H.; Saleem, A.; Zafar, B.; Sajid, M.; Ali, N.; Dar, S.H.; Shehryar, T. Detection of glaucoma using retinal fundus images: A comprehensive review. Math. Biosci. Eng. 2021, 18, 2033–2076.
  32. Ahmad, I.; Ullah, I.; Khan, W.U.; Ur Rehman, A.; Adrees, M.S.; Saleem, M.Q.; Cheikhrouhou, O.; Hamam, H.; Shafiq, M. Efficient algorithms for E-healthcare to solve multiobject fuse detection problem. J. Healthc. Eng. 2021, 2021, 9500304.
  33. Manguri, K.H.; Ramadhan, R.N.; Amin, P.R.M. Twitter sentiment analysis on worldwide COVID-19 outbreaks. Kurd. J. Appl. Res. 2020, 5, 54–65.
  34. Privor-Dumm, L.A.; Poland, G.A.; Barratt, J.; Durrheim, D.N.; Knoll, M.D.; Vasudevan, P.; Jit, M.; Bonvehí, P.E.; Bonanni, P.; International Council on Adult Immunization. A global agenda for older adult immunization in the COVID-19 era: A roadmap for action. Vaccine 2021, 39, 5240–5250.
  35. Meena, R.; Thulasi Bai, V. Russia’s COVID-19 Vaccine: Social discussion and first emotions. Res. Sq. 2020, 1–13.
  36. Alliheibi, F.M.; Omar, A.; Al-Horais, N. Opinion Mining of Saudi Responses to COVID-19 Vaccines on Twitter. Int. J. Adv. Comput. Sci. Appl. 2021, 12, 72–78.
  37. Yousefinaghani, S.; Dara, R.; Mubareka, S.; Papadopoulos, A.; Sharif, S. An analysis of COVID-19 vaccine sentiments and opinions on Twitter. Int. J. Infect. Dis. 2021, 108, 256–262.
  38. Ezhilan, A.; Dheekksha, R.; Anahitaa, R.; Shivani, R. Sentiment analysis and classification of COVID-19 tweets. In Proceedings of the 2021 5th International Conference on Trends in Electronics and Informatics (ICOEI) IEEE, Tirunelveli, India, 3–5 June 2021; pp. 821–828.
  39. Andrzejczak-Grzadko, S.; Czudy, Z.; Donderska, M. Side effects after COVID-19 vaccinations among residents of Poland. Eur. Rev. Med. Pharmacol. Sci. 2021, 25, 4418–4421.
  40. Saeed, B.Q.; Al-Shahrabi, R.; Alhaj, S.S.; Alkokhardi, Z.M.; Adrees, A.O. Side effects and perceptions following Sinopharm COVID-19 vaccination. Int. J. Infect. Dis. 2021, 111, 219–226.
  41. Dubey, A.D. Public Sentiment Analysis of COVID-19 Vaccination Drive in India. SSRN 2021, 3772401.
  42. Dumre, R.; Sharma, K.; Konar, K. Statistical and sentimental analysis on vaccination against COVID-19 in India. In Proceedings of the 2021 International Conference on Communication information and Computing Technology (ICCICT) IEEE, Mumbai, India, 25–27 June 2021; pp. 1–6.
  43. Cotfas, L.A.; Delcea, C.; Roxin, I.; Ioanăş, C.; Gherai, D.S.; Tajariol, F. The longest month: Analyzing COVID-19 vaccination opinions dynamics from tweets in the month following the first vaccine announcement. IEEE Access 2021, 9, 33203–33223.
  44. Chintalapudi, N.; Battineni, G.; Amenta, F. Sentimental analysis of COVID-19 tweets using deep learning models. Infect. Dis. Rep. 2021, 13, 329–339.
More
© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license; additional terms may apply. By using this site, you agree to the Terms and Conditions and Privacy Policy.
This entry is offline, you can click here to edit this entry!
Video Production Service
Feedback