Sentiment Analysis On Twitter Social Media Using Naїve Bayes Classifier With Swarm Particle Selection Feature Optimization And Term Frequency

Abstract

Today's social media users are very large, where everyone expresses opinions, comments, criticism and so on. This data provides valuable information that can help people or organizations in decision making. Very large amounts of data are impossible to divide humans to read and analyze manually. Sentiment Analysis is an internal process analyze, understand, and classify opinions, evaluations, judgments, attitudes, and emotions towards a particular entity such as a product, service, organization, individual, event, topic, in order to obtain information. This research aims to separate Indonesian language tweets on Twitter social media into positive, negative and neutral categories. Naїve Bayes Classifier (NBC) method with feature selection Particle Swarm Optimization (PSO) is applied to the dataset to reduce less relevant attributes during the classification process. The test results show that the Naïve Bayes Classifier algorithm with feature selection Particle Swarm Optimization (PSO) uses term frequency (TF) parameters with 97.48% accuracy.