Sentiment analysis on vaccine COVID-19 using word count and Gaussian Naïve Bayes

Abstract

Since the <span>Coronavirus disease 2019 (COVID-19) pandemic hit the world, it had a significant negative impact on individuals, governments, and the global economy. One way to reduce the negative impact of COVID-19 is to vaccinate. Briefly, vaccination aims to enable the formed immune system to remember the characteristics of the targeted viral pathogen and be able to initiate an immune response that is rapid and strong enough to defeat future live viral pathogens. However, there are still many people in the world who are anti-vaccine. This certainly greatly hampers the process of accelerating the formation of the body's immune system widely in the community. Anti-vaccine people can be found on various social media platforms. Twitter was chosen as the data source because twitter is a common source of text for sentiment analysis. This study aims to analyze public sentiment on the COVID-19 vaccine through twitter in the form of tweets and retweets. This study uses the Gaussian Naïve Bayes method to see the results of the classification of sentiment analysis. The results obtained based on experiments prove that the Gaussian Naïve Bayes method can produce an average accuracy of 97.48% for each vaccine dataset used.</span>

Factor analysis influencing Mobile JKN user experience using sentiment analysis

“…At this stage, remove meaningless words in Indonesian and English using natural language toolkit (NLTK), a Python programming library. -Stemming: words that have prefixes and suffixes are removed so that they return to their base words [15].…”

Fast Naïve Bayes classifiers for COVID-19 news in social networks

“…Among these algorithms, MNB has shown high accuracy in identifying hoaxes in social networks. In general, MNB is a probabilistic-driven algorithm for classification that measures the likelihood of a tweet belonging to a particular category based on the total of words within the tweet [6], [20]. Several investigations have compared the performance of MNB with other classification algorithms for hoax detection.…”

“…As the COVID-19 case continues, new virus variants may emerge at any time. Further, the unconfirmed information about the COVID-19 vaccine and its usefulness is spreading, leading to vaccine hesitancy among the public [6]. Real-time hoax detection for COVID-19 cases can be challenging, especially with the constant influx of new information.…”

Naive Bayes Performance in Analysis of Public Opinion Sentiment Against COVID-19

“…Sentiment Analysis is a technique of extracting text data that is used to receive information about a sentiment whether it has positive, neutral, and negative values [9]. Sentiment analysis can be used for various opinion data, such as customer satisfaction data and data on an assessment of a performance.…”

“…The Naive Bayes algorithm method is the algorithm that will be used for this research. Naive Bayes algorithm [9] is a classification method that uses probability techniques. This algorithm will perform calculations on a set of probabilities by adding up the frequencies and combinations of a dataset.…”