Analisis Sentimen Pelanggan Hotel di Purwokerto menggunakan Metode Random Forest Classifier dan Term Frequency–Inverse Document Frequency (Studi Kasus: Ulasan Pelanggan Pada Situs Tripadvisor)

Boma, Bayu Baskoro (2021) Analisis Sentimen Pelanggan Hotel di Purwokerto menggunakan Metode Random Forest Classifier dan Term Frequency–Inverse Document Frequency (Studi Kasus: Ulasan Pelanggan Pada Situs Tripadvisor). Undergraduate Thesis thesis, Institut Teknologi Telkom Purwokerto.

	Text Cover.pdf Download (346kB)
	Text Abstract.pdf Download (81kB)
	Text Abstrak.pdf Download (68kB)
	Text BAB I.pdf Download (142kB)
	Text BAB II.pdf Download (296kB)
	Text BAB III.pdf Download (354kB)
	Text BAB IV.pdf Restricted to Registered users only Download (722kB) | Request a copy
	Text BAB V.pdf Download (35kB)
	Text Daftar Pustaka.pdf Download (99kB)
	Text Lampiran.pdf Restricted to Registered users only Download (81kB) | Request a copy

Abstract

In the current millennial era, there is increasing use and familiarity with communication, media and digital technology. Therefore, e-tourism in Indonesia is growing. Many people nowadays have made hotel reservations online because it is faster, more practical and easier. As a result, the increasing number of tourists in Purwokerto every year makes tourists from outside the city make online hotel bookings in Purwokerto. For online ordering, there are already many platforms available. But previously there was an important factor in choosing the best hotel at an affordable price, namely the opinion of hotel customers from reviews in the comments column from previous hotel customers such as on the tripadvisor.co.id platform which is one of the largest travel sites in the world that helps tourists plan and. book their onward travel. This textual review is an important factor for the hotel, the hotel provider platform and the potential customers. A lot of customer review data takes a long time to figure out the polarity of positive reviews and negative reviews. A sentiment analysis model is needed to classify customer reviews into accurate positive and negative reviews. Based on previous research, the Random Forest Classifier method is a method that uses multiple decision trees in processing data. For better accuracy results, a feature selection stage is carried out using the Term Frequency – Inverse Document Frequency (TF-IDF) algorithm which has been widely used in important word assessment schemes. In this study, the Random Forest Classifier and TF-IDF methods are proposed to be used to build a sentiment analysis model using hotel customer data in Purwokerto from the internet site. The accuracy obtained from this study is 87.23%. Keywords: Sentiment Analysis, Random Forest Classifier, Term Frequency – Inverse Document Frequency.

Actions (login required)

View Item