Rahmaningrum, Silvia Astri (2019) Klasifikasi Sentimen terhadap Review Layanan Hotel Bintang Tiga di Surabaya pada Situs Traveloka Menggunakan Naive Bayes Classifier (NBC) dan Regresi Logistik Biner. Other thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
06211745000011-Undergraduate_Theses.pdf - Published Version Download (2MB) | Preview |
Abstract
Pemanfaatan situs media sosial seperti Traveloka dapat membantu pemasaran hotel dengan menyediakan informasi berupa ulasan terkait pencarian dan pemesanan hotel secara online. Ulasan yang diberikan bisa menjadi feedback bagi hotel terkait serta bisa membantu pengunjung dalam memilih hotel yang tepat. Informasi feedback berupa ulasan merupakan data teks penting sehingga diperlukan suatu metode untuk mengklasifikasikannya. Sumber data didapatkan dari proses web scraping yang bertujuan untuk mendapatkan data secara online pada halaman website dengan mengumpulkan review pengunjung Favehotel dan Hotel Gunawangsa yang bersumber dari situs Traveloka. Penelitian ini menggunakan Naïve Bayes Classifier (NBC) dan Regresi Logistik Biner yang mana labelling sentimen dilakukan berdasarkan lexicon based. Visualisasi word cloud menunjukkan bahwa kata kunci yang terbanyak yang mengarah pada kedua hotel dengan sentimen positif terbesar yaitu kata ‘bersih’ dan ‘nyaman’. Perbandingan metode antara NBC dan Regresi Logistik Biner untuk Favehotel dan Hotel Gunawangsa didapatkan keputusan bahwa metode Regresi Logistik Biner dengan SMOTE lebih baik jika dibandingkan dengan NBC yang mana nilai AUC pada data testing untuk Favehotel sebesar 0,84 dan Hotel Gunawangsa sebesar 0,82.
==============================================================================================================================
Utilization of social media sites such as Traveloka can help hotel marketing by providing information as review related to search and hotel bookings online. The given review could be a feedback to the related hotel as well as to assist visitors in choosing the right hotel. Feedback information as a review is important data text so needs a method to classifiy it. Sources of data are obtained from web scraping process which that aims to obtain online data on website page by collecting visitor review of Favehotel and Gunawangsa Hotel sourced from Traveloka sites. This study using Naïve Bayes Classifier (NBC) and Binary Logistic Regression which is the process of sentiment labeling based on Lexicon dictionary. Word cloud visualization shows that the highest keywords that lead to the both of the hotel with the largest positive sentiment are 'clean' and 'comfortable'. A comparison methods between NBC and Binary Logistic Regression for Favehotel and Gunawangsa Hotel obtained a decision that Binary Logistic Regression method with SMOTE was better than NBC where AUC value in testing data for Favehotel was 0,84 and Hotel Gunawangsa was 0,82.
| Item Type: | Thesis (Other) |
|---|---|
| Additional Information: | RSSt 519.536 Rah k-1 2019 |
| Uncontrolled Keywords: | Hotel, Naïve Bayes Classifier, Regresi Logistik Biner, Traveloka |
| Subjects: | H Social Sciences > HA Statistics Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression T Technology > T Technology (General) > T57.5 Data Processing |
| Divisions: | Faculty of Mathematics, Computation, and Data Science > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Rahmaningrum Silvia Astri |
| Date Deposited: | 29 Dec 2022 08:09 |
| Last Modified: | 29 Dec 2022 08:09 |
| URI: | http://repository.its.ac.id/id/eprint/64473 |
Actions (login required)
 |
View Item |