Analisis Sentimen Mengenai Gangguan Bipolar Pada Twitter Menggunakan Algoritma Naïve Bayes

Abstract

Bipolar disorder is one of the world's most common mental health disorders. To find out public sentiment regarding bipolar disorder, sentiment analysis is carried out through social media to analyze positive or negative sentiments with the aim of maintaining positive sentiment towards the problem of bipolar disorder. Twitter is a social media that is often used to exchange information, discuss, and even express emotions. The emotions of Twitter users can be called sentiment. Sentiment analysis is also carried out to see opinions or tendencies towards an opinion. Opinion tendencies can be in the form of positive or negative sentiments. The data used in this study uses the bipolar keyword. There are 2177 tweets data that were successfully obtained in the crawling process using API key access from Twitter developers, after which the data will be processed using preprocessing. The comparison of the presentations obtained is 70.92% expressing a negative opinion and 29.08% expressing a favorable opinion. The analysis results in this study using the nave Bayes algorithm is with an accuracy value of 92.110092%.