Analisis Sentimen Opini Pengguna Twitter Terhadap Perusahaan Jasa Ekspedisi Menggunakan Algoritma Naïve Bayes Berbasis PSO

Abstract

Expeditions are used in the process of delivering goods or selling them remotely. Twitter has become a social media for information sharing and opinions, including those on the expeditionary services both negative and positive. The solution for the problem which occurs is that of sentiment analysis, helpful in grouping the data and predicting the tweet. The aim of the research to predict sentient tweeted data using a file classification method, naive bayes's algorithm calculated the value of the tweets of the Anteraja expedition service that had the results accuracy 87,77%, precision 76,67%, recall 52,27%. JNE with accuracy 81,48%, precision 71,43%, dan recall 62,50%. JNT with accuracy 91,46%, precision 48,15%, recall 86,67%. Shopee Express with accuracy 92,68%, precision 9,09%, recall 16,67% and Sicepat with accuracy 91,50%, presision 100,00% dan recall 38,10%. Particle Swarm Optimization (PSO) serves to increase the value of the results of the nave Bayes classification with the results of Anteraja accuracy 91,70%, precision 82,05%, recall 72,73%. JNE accuracy 93,83%, precision 88,00%, recall 91,67%. JNT accuracy 92,18%, precision 70,97%, recall 81,48%. Shopee Express accuracy 94%, precision 20,00%, recall 33,33% and Sicepat accuracy 95,42%, precision 93,75%, recall 71,43%. From the results of naïve bayes research and Particle Swarm Optimization (PSO) it can be compared that Particle Swarm Optimization (PSO) is proven to be able to increase the value of nave Bayes.