Pengukuran Kinerja Optimasi Algoritma Bat Pada Algoritma Naive Bayes, KNN Dan Decision Tree Untuk Sentimen Analisis Di Lini Masa Twitter

Social media is a very effective communication in today's digital era. Of the social media, Twitter most widely used media. Many tweets entered on have encouraged research field of text mining. One branches mining sentiment analysis. Sentiment analysis this study was formed from 3 classification algorithms, namely Naïve Bayes and Decission Tree. In practice, results algorithms often produce low levels accuracy. Bat algorithm an that can optimize accuracy Bayes, K-NN study, two scenarios were made: first, calculating algorithm, Second, optimizing with method, which then re-tested value. first scenario percentage generated value 33,58, 33,61 Tree 32,82. second scenario, using one objective functions, f(x) = x2, obtained 39,01, 66,15 76,63. From optimization test Algorithm, it found overall functions all able to increase data before optimization. tests, Decision has highest average increment, 43,81 %