In Disaster medicine and public health preparedness
OBJECTIVES : The present study aims to examine COVID-19 vaccination discussions on Twitter in Turkey and conduct sentiment analysis.
METHODS : The current study performed sentiment analysis of Twitter data with artificial intelligence (AI)'s Natural Language Processing (NLP) method. The tweets were retrieved retrospectively from March 10, 2020, when the first Covid-19 case was seen in Turkey, to April 18, 2022. 10308 tweets accessed. The data were filtered before analysis due to excessive noise. First, the text is tokenized. Many steps were applied in normalizing texts. Tweets about the COVID-19 vaccines were classified according to basic emotion categories using sentiment analysis. The resulting dataset was used for training and testing machine learning classifiers.
RESULTS : It was determined that 7.50% of the tweeters had positive, 0.59% negative, and 91.91% neutral opinions about the COVID-19 vaccination. When the accuracy values of the ML algorithms used in this study were examined, it was seen that the XGB algorithm had higher scores.
CONCLUSIONS : Three out of four tweets consist of negative and neutral emotions. The responsibility of professional chambers and the public is essential in transforming these neutral and negative feelings into positive ones.
Özsezer Gözde, Mermer Gülengül
2022-Oct-13
COVID-19, Twitter, Vaccine, sentiment analysis
