Next Article in Journal
COVID-19 Pandemic and Quality of Life among Romanian Athletes
Previous Article in Journal
Physical and Physiological Predictors of FRAN CrossFit® WOD Athlete’s Performance
Open AccessArticle

Applying Machine Learning to Identify Anti-Vaccination Tweets during the COVID-19 Pandemic

1
Physical Activity Research Group, Appleton Institute, Central Queensland University, Rockhampton, QLD 4701, Australia
2
Public Health Faculty, University of Medicine and Pharmacy at Ho Chi Minh City, Ho Chi Minh City 700000, Vietnam
3
Trung Vuong Hospital, Ho Chi Minh City 700000, Vietnam
*
Author to whom correspondence should be addressed.
Academic Editors: Paul B. Tchounwou and Quyen G. To
Int. J. Environ. Res. Public Health 2021, 18(8), 4069; https://doi.org/10.3390/ijerph18084069
Received: 21 March 2021 / Revised: 5 April 2021 / Accepted: 8 April 2021 / Published: 12 April 2021
(This article belongs to the Special Issue Machine Learning Applications in Public Health)
Anti-vaccination attitudes have been an issue since the development of the first vaccines. The increasing use of social media as a source of health information may contribute to vaccine hesitancy due to anti-vaccination content widely available on social media, including Twitter. Being able to identify anti-vaccination tweets could provide useful information for formulating strategies to reduce anti-vaccination sentiments among different groups. This study aims to evaluate the performance of different natural language processing models to identify anti-vaccination tweets that were published during the COVID-19 pandemic. We compared the performance of the bidirectional encoder representations from transformers (BERT) and the bidirectional long short-term memory networks with pre-trained GLoVe embeddings (Bi-LSTM) with classic machine learning methods including support vector machine (SVM) and naïve Bayes (NB). The results show that performance on the test set of the BERT model was: accuracy = 91.6%, precision = 93.4%, recall = 97.6%, F1 score = 95.5%, and AUC = 84.7%. Bi-LSTM model performance showed: accuracy = 89.8%, precision = 44.0%, recall = 47.2%, F1 score = 45.5%, and AUC = 85.8%. SVM with linear kernel performed at: accuracy = 92.3%, Precision = 19.5%, Recall = 78.6%, F1 score = 31.2%, and AUC = 85.6%. Complement NB demonstrated: accuracy = 88.8%, precision = 23.0%, recall = 32.8%, F1 score = 27.1%, and AUC = 62.7%. In conclusion, the BERT models outperformed the Bi-LSTM, SVM, and NB models in this task. Moreover, the BERT model achieved excellent performance and can be used to identify anti-vaccination tweets in future studies. View Full-Text
Keywords: deep learning; neural network; LSTM; BERT; transformer; stance analysis; vaccine deep learning; neural network; LSTM; BERT; transformer; stance analysis; vaccine
MDPI and ACS Style

To, Q.G.; To, K.G.; Huynh, V.-A.N.; Nguyen, N.T.Q.; Ngo, D.T.N.; Alley, S.J.; Tran, A.N.Q.; Tran, A.N.P.; Pham, N.T.T.; Bui, T.X.; Vandelanotte, C. Applying Machine Learning to Identify Anti-Vaccination Tweets during the COVID-19 Pandemic. Int. J. Environ. Res. Public Health 2021, 18, 4069. https://doi.org/10.3390/ijerph18084069

AMA Style

To QG, To KG, Huynh V-AN, Nguyen NTQ, Ngo DTN, Alley SJ, Tran ANQ, Tran ANP, Pham NTT, Bui TX, Vandelanotte C. Applying Machine Learning to Identify Anti-Vaccination Tweets during the COVID-19 Pandemic. International Journal of Environmental Research and Public Health. 2021; 18(8):4069. https://doi.org/10.3390/ijerph18084069

Chicago/Turabian Style

To, Quyen G.; To, Kien G.; Huynh, Van-Anh N.; Nguyen, Nhung T.Q.; Ngo, Diep T.N.; Alley, Stephanie J.; Tran, Anh N.Q.; Tran, Anh N.P.; Pham, Ngan T.T.; Bui, Thanh X.; Vandelanotte, Corneel. 2021. "Applying Machine Learning to Identify Anti-Vaccination Tweets during the COVID-19 Pandemic" Int. J. Environ. Res. Public Health 18, no. 8: 4069. https://doi.org/10.3390/ijerph18084069

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop