Implementasi Algoritma Decision Tree dan Naïve Bayes Untuk Klasifikasi Sentimen Terhadap Kepuasan Pelanggan Starbucks

Indonesia is included in the category of countries with largest population world, this situation a business opportunity for entrepreneurs who enter coffee shop industry market. Researchers utilize one grouping methods, namely data mining classification order to help entities identify different groups Starbucks customer satisfaction database. The purpose research be able group categories into 3 classes, satisfied, quite satisfied and dissatisfied using Decision Tree & Naive Bayes algorithm. So that it can find out public opinion on satisfaction, study aim was obtain accuracy, precision recall values best algorithm satisfaction. In test obtained from tweets keyword "Starbucks" Twitter. results where sentiment process neutral category, seen reviews keywords "starbuck OR starbucks #starbucks "The were positive comments 476 percentage 19.2%, 1743 70.3% negative 258 10.4%, so conclusions drawn based polarity calculation, stabuck have category.In study, concluded performance better than algorithm, as following explanation.The an accuracy 83%. Naïve value by 74%.