KOMPARASI METODE SVM, K-NN DAN NBC PADA ANALISIS SENTIMEN

The beauty of Bali raises many comments about how a trip to Indonesia is not complete without going Bali. In the tourism industry application tourist satisfaction and perspective very important, but most them still apply surveys. survey-based approach has weaknesses such as operational costs, potential for data duplication, lack comprehensiveness. Sentiment analysis natural objects performed by classifying positive negative in Jatiluwih comment dataset. focus this panel's sentiment on related Natural Tourism Attractiveness Criteria. According Directorate General Forest Protection Nature Conservation 2003, criteria are attraction, market potential, accessibility, socio-economic environmental conditions, public services, climate supporting facilities infrastructure, availability safety clean water. This study compares SVM, K-NN, NBC methods. aims provide comprehensive performance each method using confusion matrix. results showed that K-NN was superior SVM terms testing accuracy precision, where gave value 93.4%, 93.1%, 87.9%.