Saputri, Rahayu Prihatini (2019) Klasifikasi Sentimen Wisatawan Candi Borobudur pada Situs TripAdvisor menggunakan Support Vector Machine dan K-Nearest Neighbor. Other thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
06211540000040-Undergraduate_Theses.pdf Download (2MB) | Preview |
Abstract
Candi Borobudur merupakan salah satu destinasi wisata di Indonesia yang saat ini menjadi satu dari sepuluh destinasi yang diprioritaskan oleh Kementerian Pariwisata. Untuk memajukan wisata Candi Borobudur, pihak pengelola wisata perlu mengetahui berbagai persepsi dari wisatawan. Oleh sebab itu diperlukan suatu teknik untuk mendapatkan sentimen wisatawan dari ulasan yang tersedia di situs TripAdvisor dengan metode klasifikasi. Pada penelitian ini digunakan metode K-Nearest Neighbor (K-NN) dan Support Vector Machine (SVM), yang disertai dengan penerapan N-gram sebagai teknik penggabungan beberapa kata berurutan dan Synthetic Minority Oversampling Technique (SMOTE) untuk mengatasi kasus data imbalance. Hasil dari penelitian ini menunjukkan bahwa metode terbaik yang dapat diterapkan untuk mengklasifikasikan sentimen wisatawan Candi Borobudur adalah SVM kernel Radial Basis Function (RBF) yang disertai dengan menerapkan teknik unigram. Kinerja klasifikasi yang dihasilkan oleh metode ini tergolong sangat baik.
================================================================================================================================
Borobudur Temple is one of the destinastions in Indonesia which is currently one of ten destinations prioritized by the Ministry of Tourism. The manager needs to know various perceptions from visitors to advance the destinations. Therefore, a technique is needed to get visitor sentiments from the reviews on the TripAdvisor site with classification method. The methods used in this study are K-Nearest Neighbor (K-NN) and Support Vector Machine (SVM), which are accompanied by the application of N-gram as a technique of combining sequential words and Synthetic Minority Oversampling Technique (SMOTE) to handle imbalanced dataset. The results of this study indicate that the best method that can be applied to classify visitor sentiments of Borobudur Temple is SVM with Radial Basis Function (RBF) kernel and apply the unigram technique. This method shows a very good classification performance.
| Item Type: | Thesis (Other) |
|---|---|
| Additional Information: | RSSt 519.536 Sap k-1 2019 |
| Uncontrolled Keywords: | K-Nearest Neighbor, N-gram, Sentimen, Synthetic Minority Oversampling Technique, Support Vector Machine |
| Subjects: | Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science) |
| Divisions: | Faculty of Mathematics, Computation, and Data Science > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Rahayu Prihatini Saputri |
| Date Deposited: | 29 May 2023 02:41 |
| Last Modified: | 29 May 2023 02:41 |
| URI: | http://repository.its.ac.id/id/eprint/63911 |
Actions (login required)
 |
View Item |