Skripsi

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

---

Penilaian

---

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.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2107002698	T48603	T486032021	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T486032021

Publisher

Inderalaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2021

Collation

xvii, 165 hlm,: ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

004.07

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Pemrosesan Data, Teknik Informatika
Prodi Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

MURZ

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment