SENTIMEN ANALISIS UNTUK MEMBANDINGKAN KINERJA PADA TRAVELOKA DAN TIKET.COM

Prastyo, Mugi (2019) SENTIMEN ANALISIS UNTUK MEMBANDINGKAN KINERJA PADA TRAVELOKA DAN TIKET.COM. Other thesis, Universitas Amikom Purwokerto.

[img] Text
Cover.pdf

Download (1MB)
[img] Text
DAFTAR ISI.pdf

Download (548kB)
[img] Text
ABSTRAK.pdf

Download (630kB)
[img] Image
BAB I.pdf
Restricted to Registered users only

Download (548kB)
[img] Image
BAB II.pdf
Restricted to Registered users only

Download (938kB)
[img] Image
BAB III.pdf
Restricted to Registered users only

Download (575kB)
[img] Image
BAB IV.pdf
Restricted to Registered users only

Download (2MB)
[img] Image
BAB V.pdf
Restricted to Registered users only

Download (626kB)
[img] Image
DAFTAR PUSTAKA.pdf
Restricted to Registered users only

Download (640kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository staff only

Download (1MB)

Abstract

Internet users in Indonesia are always experiencing an increase. With the increase in internet users in Indonesia, many companies are used by most companies in Indonesia engaged in e-commerce, especially in the sale of tickets, plane tickets, train tickets, travel tickets and others. Traveloka and Tiket.com is an e-commerce company which is engaged in airplane ticket reservations and online hotel reservations that provide travel services. In an e-commerce system or application, it must have shortcomings that are often felt by its users. By analyzing application users, companies can understand the shortcomings of the application and the expectations of its users. The purpose of this research is to measure the performance of Traveloka and Tiket.com by comparing using sentiment analysis. Then labeling and analyzing using Naïve Bayes Classifier to classify reviews based on positive sentiment class and negative sentiment class. Then visualized the information that is often reviewed using charts. Through the classification obtained the greatest accuracy using the Naïve Bayes Classifier at Traveloka by 37,88%.. As well as positive reviews that are often reviewed namely "very" the word "very" often app ears together with the word "help", which shows that this application can help for its users. While negative reviews that are often reviewed are "disappointed". At Tiket.com, the biggest accuracy obtained by using Naïve Bayes Classifier is 52,22 %. And positive reviews that are often reviewed are "very" While negative reviews that are often reviewed are "please".

Item Type: Thesis (Other)
Additional Information: Dosen Pembimbing: Rahman Rosyidi, M.Kom.
Uncontrolled Keywords: Text Mining, Naïve Bayes Classifier, Sentiment Analysi
Subjects: H Social Sciences > HF Commerce
H Social Sciences > HG Finance
T Technology > T Technology (General)
Divisions: Fakultas Ilmu Komputer > Sistem Informasi
Depositing User: UPT Perpustakaan Pusat Universitas Amikom Purwokerto
Date Deposited: 04 Nov 2020 02:10
Last Modified: 04 Nov 2020 02:10
URI: http://eprints.amikompurwokerto.ac.id/id/eprint/350

Actions (login required)

View Item View Item