ANALISA SENTIMEN MASYARAKAT TERHADAP KEBIJAKAN VAKSINASI COVID-19 DI INDONESIA PADA TWITTER MENGGUNAKAN ALGORITMA LSTM

Indonesia was shocked by the emergence of the first case of Covid-19 in March 2020. To slow the spread of the Covid-19 virus, the Government made a policy of Large-Scale Social Restrictions. With this policy, almost all educational and office activities are carried out online. The Covid-19 virus can be fought with herd immunity. One way to produce herd immunity is by giving vaccines or vaccinations. On December 16, 2020, President Joko Widodo announced that the Covid-19 vaccine would be available free of charge to all Indonesians. Of course, the information received various responses from the public. One of them was through Twitter, various tweets about vaccination appeared on the Twitter homepage. Some opinions support and some reject vaccination. To find out the opinion of public sentiment regarding vaccination, a sentiment analysis process is carried out using an algorithm that aims to assist the sentiment analysis process with quite a lot of data. In this study, the sentiment analysis process uses one of the deep learning methods, namely LSTM (Long Short-Term Memory), because LSTM (Long Short-Term Memory) is one of the deep learning methods that can perform the sentiment analysis process of Indonesian texts and research that using LSTM (Long Short-Term Memory) to analyze public sentiment regarding vaccination policy is still not available. The results of this study tend to support the vaccination program by producing 79% positive tweets, 13% neutral tweets and 8% negative tweets and getting a model accuracy of 71% using parameters of 15 epochs, 64 batch sizes and a comparison of training data and test data of 9:1 (3600:400).