Analisis Sentimen Dengan Metode Naïve Bayes, SMOTE Dan Adaboost Pada Twitter Bank BTN

Kurnia (Universitas Nusa Mandiri)
Indah Purnamasari (Universitas Nusa Mandiri)
Dedi Dwi Saputra (Universitas Nusa Mandiri)

Jurnal JTIK (Jurnal Teknologi Informasi dan Komunikasi)
Vol 7 No 2 (2023): APRIL-JUNE 2023

Social media has become a means of sharing information with each other, from being a means of promotion to being used to spread opinions. Because of the ease of technology, anyone can access social media and comment on issues that are being discussed. Branding image is also an important thing, because people can interact directly through social media, be it support or criticism. So this study was conducted to analyze the sentiment on twitter towards Bank BTN as a bank that has long focused on housing loans. To analyze the sentiment, an experiment was carried out by a combination of SMOTE, Naïve Bayes and Adaboost algorithms. Before calculating the algorithm, stemming and stopwords are carried out so that the data used does not contain noise. The results showed that the combination of SMOTE, Naïve Bayes, and Adaboost showed the best modeling results with an accuracy of 87.05%, precision of 90.63%, recall of 83.00%, and AUC of 0.909.