Analisis Sentimen Pariwisata di Kota Malang Menggunakan Metode Naive Bayes dan Seleksi Fitur Query Expansion Ranking

Shima Fanissa (Fakultas Ilmu Komputer, Universitas Brawijaya)
Mochammad Ali Fauzi (Fakultas Ilmu Komputer, Universitas Brawijaya)
Sigit Adinugroho (Fakultas Ilmu Komputer, Universitas Brawijaya)

Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Vol 2 No 8 (2018): Agustus 2018

Tourism is one of effort to promote a city. Malang currently has a branding city called "Beautiful Malang". Indonesian choose Malang tourism as a destination and review it on the website, one of them is TripAdvisor. Thus this research tried to analyze the reviews from the public about the tourism of Malang City through sentiment analysis and classified into two classes, that is positive and negative. In this research the method used is Naive Bayes with Query Expansion Ranking feature selection to reduce the number of features in the classification process. The process of sentiment analysis consists of preprocessing, feature selection with Query Expansion Ranking method, and classification with Naive Bayes. This research is testing the accuracy by using the variation of feature selection ratio, the result of 75% feature selection has the best accuracy of 86.6%.