Analisa Sentimen Drama Korea Melalui Media Sosial X dengan Menggunakan Algoritma Naïve Bayes

Abstract

In this digital era, technological advancements allow easy access to various social media platforms, including Twitter or X, which has over 500 million users. This platform is often used to share opinions through the concept of microblogging. In Indonesia, Korean trends like K-Pop and K-Drama are highly popular, sparking various discussions on social media, especially on X, generating both positive and negative opinions. Sentiment analysis is an effective method for extracting public opinion from large text data, such as those found on X, by classifying comments into positive and negative classes using the Naïve Bayes method. Tweets were collected from X using hashtags related to Korean dramas. The data was then cleaned and processed for sentiment analysis using Naïve Bayes. The Naïve Bayes algorithm is based on Bayes' theorem and is often used in sentiment analysis due to its accuracy and speed in producing results. This study achieved a precision rate of 88.44%. For negative sentiment data, precision was 67.86%, and recall (specificity) for negative sentiment was 59.38%, indicating that the model is quite good at identifying truly negative data. Meanwhile, recall for positive sentiment reached 91.70%. The model's accuracy was 84.33%, showing that the algorithm used can classify sentiment well with the given data. These results can be useful for content creators, marketers, and cultural and social research