KLASIFIKASI KOMENTAR PENGUNJUNG HOTEL MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE DAN SELEKSI FITUR INFORMATION GAIN

NOTONEGORO, PRAYOGI and Abdiansah, Abdiansah and Utami, Alvi Syahrini (2021) KLASIFIKASI KOMENTAR PENGUNJUNG HOTEL MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE DAN SELEKSI FITUR INFORMATION GAIN. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021181722001.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_55201_0902118172001_Turnitin.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (16MB) | Request a copy
Preview	Text RAMA_55201_09021181722001_0001108401_0022127804_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_55201_09021181722001_0001108401_0022127804_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (656kB) | Request a copy
	Text RAMA_55201_09021181722001_0001108401_0022127804_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (646kB) | Request a copy
	Text RAMA_55201_09021181722001_0001108401_0022127804_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021181722001_0001108401_0022127804_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021181722001_0001108401_0022127804_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (134kB) | Request a copy
	Text RAMA_55201_09021181722001_0001108401_0022127804_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (67kB) | Request a copy

Abstract

Hotel visitor comments is one of the basics of the hotel in understanding the needs of visitors to improve hotel services and facilities. This study discussed how to understand the needs of visitors in order to compete with other competitors. Sentiment analysis was used to solve this problem by classifying comments into positive and negative comments using a classification algorithm. Support Vector Machine is one of the classification algorithms that is commonly used, but it lacks the problem of feature selection. Feature selection is needed to solve this problem. Information Gain is one of the filtering feature selection methods in selecting relevant features. The results of the comments classification research using the Support Vector Machine get the best accuracy value in the linear kernel, parameter C: 1 with accuracy results: 0.98, and computation time 0.16 seconds. The addition of the Information Gain feature selection at the value of K: 0.2 was proven to be able to accelerate the computation time from 0.16 seconds to 0.13 seconds without reducing the accuracy value. The addition was succeed in reducing the number of features which can reduce the error of the algorithm model in classifying features. This was proven by the increased accuracy in the Kernel Rbf C: 0.1 K: 0.2 with an increase of 0.5, from 0.86 to 0.91.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Analisa Sentimen, Hotel, Information Gain, Support Vector Machine, Seleksi fitur
Subjects:	T Technology > T Technology (General) > T175-178 Industrial research. Research and development > T175 General works T Technology > T Technology (General) > T58.5-58.64 Information technology > T58.6.E9 Management information systems -- Congresses.
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Prayogi Notonegoro
Date Deposited:	24 Jun 2021 07:25
Last Modified:	24 Jun 2021 07:25
URI:	http://repository.unsri.ac.id/id/eprint/48603

Actions (login required)

View Item