Perbandingan Algoritma Naïve Bayes dan LSTM untuk Analisis Sentimen Terhadap Opini Masyarakat Tentang Sandwich Generation

Sandwich Generation is a term for a group of people who have elderly parents and children, so they have to take care of both generations. Opinions about this phenomenon have elicited various responses on social media twitter, which requires in-depth analysis. This study identifies the problems of the lack of research comparing the performance of Naïve Bayes and LSTM algorithms in analyzing public opinion sentiment about the sandwich generation, the complexity of social media data analysis with the characteristics of informal language, abbreviations, and symbols that are difficult to analyze manually, the need to explore the algorithm's ability to classify sentiment, and determine the most accurate method to analyze public opinion sentiment. Sentiment analysis is used to evaluate opinions, feedback, and emotions by classifying texts into positive, negative, or neutral categories. The results obtained from this study are that the LSTM method has better performance when compared to Naive Bayes. The LSTM method produced an accuracy, precision and recall value of 91.85%. while the Naive Bayes method has an accuracy value of 83%, precision of 90% and recall of 82%.