ANALISIS SENTIMEN ULASAN CANDI BOROBUDUR PADA TRIPADVISOR MENGGUNAKAN SUPPORT VECTOR MACHINE

Nadhira Haifa Firdausi, - (2024) ANALISIS SENTIMEN ULASAN CANDI BOROBUDUR PADA TRIPADVISOR MENGGUNAKAN SUPPORT VECTOR MACHINE. S1 thesis, Universitas Pendidikan Indonesia.

	Text S_KOM_1908046_Title.pdf Download (498kB)
	Text S_KOM_1908046_Chapter1.pdf Download (285kB)
	Text S_KOM_1908046_Chapter2.pdf Restricted to Staf Perpustakaan Download (1MB)
	Text S_KOM_1908046_Chapter3.pdf Restricted to Staf Perpustakaan Download (179kB)
	Text S_KOM_1908046_Chapter4.pdf Restricted to Staf Perpustakaan Download (2MB)
	Text S_KOM_1908046_Chapter5.pdf Download (215kB)
	Text S_KOM_1908046_Appendix.pdf Restricted to Staf Perpustakaan Download (491kB)

Abstract

Industri pariwisata global, termasuk Indonesia, mengalami dampak mendalam dari pandemi COVID-19, yang ditandai dengan penurunan jumlah pengunjung internasional dan domestik pasca-2019. Sebagai tanggapan, Indonesia menerapkan inisiatif Destinasi Super Prioritas dengan fokus terutama pada situs seperti Candi Borobudur di Pulau Jawa, yang diakui dunia karena signifikansi budaya dan sejarahnya sebagai situs Warisan Dunia UNESCO. Penelitian ini bertujuan untuk melakukan analisis sentimen ulasan TripAdvisor berbahasa Inggris tentang Candi Borobudur dengan menggunakan Support Vector Machine untuk klasifikasi. Data yang digunakan dalam penelitian ini dikumpulkan dari Oktober 2005 hingga Mei 2024. Studi ini mencakup berbagai tahap: mulai dari pengumpulan data dan preprocessing teks hingga pembagian data untuk pelatihan dan pengujian, anotasi manual label sentimen, ekstraksi fitur TF-IDF, pelatihan model SVM, dan evaluasi kinerja. Akurasi 80%, dengan skor F1 0,77, presisi 0,78, dan recall 0,83. The global tourism industry, including Indonesia, experienced profound repercussions from the COVID-19 pandemic, marked by a notable downturn in international and domestic visitor numbers post-2019. In response, Indonesia implemented the Super Priority Destinations initiative, focusing particularly on iconic sites such as Candi Borobudur on Java Island, recognized worldwide for its cultural and historical significance as a UNESCO World Heritage site. This research utilizes Support Vector Machine (SVM) for sentiment analysis of English-language TripAdvisor reviews of Candi Borobudur, leveraging TripAdvisor's role as a pivotal platform for travelers to express opinions and share experiences. The data used in this study was collected from October 2005 to May 2024. The study encompasses various stages: from data collection and text preprocessing to partitioning data for training and testing, manual annotation of sentiment labels, TF-IDF feature extraction, SVM model training, and subsequent performance evaluation. Achieving an accuracy of 83%, with an F1-score of 0.77, precision of 0.78, and recall of 0.83.

Item Type:	Thesis (S1)
Additional Information:	https://scholar.google.com/citations?user=2kpQNfoAAAAJ&hl=en
Uncontrolled Keywords:	Pariwisata, Sentimen Analisis, Support Vector Machine, Borobudur, TripAdvisor Tourism, Sentiment Analysis, Support Vector Machine, Borobudur, TripAdvisor
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software
Divisions:	Fakultas Pendidikan Matematika dan Ilmu Pengetahuan Alam > Program Studi Ilmu Komputer
Depositing User:	Nadhira Haifa Firdausi
Date Deposited:	05 Sep 2024 08:24
Last Modified:	05 Sep 2024 08:24
URI:	http://repository.upi.edu/id/eprint/122805

Actions (login required)

View Item