Vaccine Hesitancy on Social Media: Sentiment Analysis from June 2011 to April 2019

被引:89
作者
Piedrahita-Valdes, Hilary [1 ]
Piedrahita-Castillo, Diego [2 ]
Bermejo-Higuera, Javier [2 ]
Guillem-Saiz, Patricia [3 ,4 ]
Ramon Bermejo-Higuera, Juan [2 ]
Guillem-Saiz, Javier [5 ]
Antonio Sicilia-Montalvo, Juan [2 ]
Machio-Regidor, Francisco [2 ]
机构
[1] Univ Valencia, Dept Prevent Med & Publ Hlth Bromatol Toxicol & L, Valencia 46010, Spain
[2] Int Univ La Rioja, Fac Engn & Technol, Logrono 26006, Spain
[3] European Univ Valencia, Dept Prevent Dent Epidemiol & Publ Hlth, Valencia 46010, Spain
[4] Inst Hlth Carlos III, CIBER Physiopathol Obes & Nutr CIBERobn, Madrid 28029, Spain
[5] Int Univ Valencia, Dept Psychol, Valencia 46002, Spain
关键词
vaccine hesitancy; vaccination; opinion mining; sentiment analysis; content analysis; machine learning; social media; Twitter;
D O I
10.3390/vaccines9010028
中图分类号
R392 [医学免疫学]; Q939.91 [免疫学];
学科分类号
100102 ;
摘要
Vaccine hesitancy was one of the ten major threats to global health in 2019, according to the World Health Organisation. Nowadays, social media has an important role in the spread of information, misinformation, and disinformation about vaccines. Monitoring vaccine-related conversations on social media could help us to identify the factors that contribute to vaccine confidence in each historical period and geographical area. We used a hybrid approach to perform an opinion-mining analysis on 1,499,227 vaccine-related tweets published on Twitter from 1st June 2011 to 30th April 2019. Our algorithm classified 69.36% of the tweets as neutral, 21.78% as positive, and 8.86% as negative. The percentage of neutral tweets showed a decreasing tendency, while the proportion of positive and negative tweets increased over time. Peaks in positive tweets were observed every April. The proportion of positive tweets was significantly higher in the middle of the week and decreased during weekends. Negative tweets followed the opposite pattern. Among users with >= 2 tweets, 91.83% had a homogeneous polarised discourse. Positive tweets were more prevalent in Switzerland (71.43%). Negative tweets were most common in the Netherlands (15.53%), Canada (11.32%), Japan (10.74%), and the United States (10.49%). Opinion mining is potentially useful to monitor online vaccine-related concerns and adapt vaccine promotion strategies accordingly.
引用
收藏
页码:1 / 12
页数:12
相关论文
共 38 条
[1]  
Ali I., 2017, Int. J. Multidisciplinary Sci. And Eng., V8, P28
[2]   A lexicon based method to search for extreme opinions [J].
Almatarneh, Sattam ;
Gamallo, Pablo .
PLOS ONE, 2018, 13 (05)
[3]   Vaccine hesitancy among parents in a multi-ethnic country, Malaysia [J].
Azizi, Fatin Shaheera Mohd ;
Kew, Yueting ;
Moy, Foong Ming .
VACCINE, 2017, 35 (22) :2955-2961
[4]  
Behdenna S., 2018, EAI Endorsed Transactions on Context-Aware Systems and Applications, V4, pe2, DOI [10.4108/eai.14-3-2018.154339, DOI 10.4108/EAI.14-3-2018.154339]
[5]   Debunking Vaccination Myths: Strong Risk Negations Can Increase Perceived Vaccination Risks [J].
Betsch, Cornelia ;
Sachse, Katharina .
HEALTH PSYCHOLOGY, 2013, 32 (02) :146-155
[6]  
Blankenship Elizabeth B, 2018, Perm J, V22, P17, DOI 10.7812/TPP/17-138
[7]   Weaponized Health Communication: Twitter Bots and Russian Trolls Amplify the Vaccine Debate [J].
Broniatowski, David A. ;
Jamison, Amelia M. ;
Qi, SiHua ;
AlKulaib, Lulwah ;
Chen, Tao ;
Benton, Adrian ;
Quinn, Sandra C. ;
Dredze, Mark .
AMERICAN JOURNAL OF PUBLIC HEALTH, 2018, 108 (10) :1378-1384
[8]   Affective Computing and Sentiment Analysis [J].
Cambria, Erik .
IEEE INTELLIGENT SYSTEMS, 2016, 31 (02) :102-107
[9]  
Celebi M. E., 2016, Unsupervised Learning Algorithms, DOI 10.1007/978-3-319-24211-8
[10]  
Chauhan P., 2017, International Journal for Research in Applied Science and Engineering Technology, VV, P80, DOI [DOI 10.22214/IJRASET.2017.11011, 10.22214/ijraset.2017, DOI 10.22214/IJRASET.2017]