Analisis Sentimen Pengguna Twitter Terhadap Layanan Aplikasi Dompet Digital dengan Metode Support Vector Machine (SVM) dan Convolutional Neural Network (CNN)

Pambudi, Ardiansyah Setyo (2021) Analisis Sentimen Pengguna Twitter Terhadap Layanan Aplikasi Dompet Digital dengan Metode Support Vector Machine (SVM) dan Convolutional Neural Network (CNN). Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

Text 062117 4000 0058-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2023. Download (1MB) | Request a copy

Abstract

Aplikasi dompet digital merupakan metode pembayaran
baru yang sedang tren di Indonesia. Terdapat banyak aplikasi
dompet digital yang ada di masyarakat dengan fitur
keunggulannya masing-masing. Penilaian masyarakat terhadap
layanan dompet digital dapat diperoleh melalui media sosial.
Penelitian ini dilakukan untuk mengetahui tanggapan masyarakat
tentang layanan dompet digital berdasarkan sentimen masyarakat
dengan menggunakan data hasil crawling dari dua kata kunci
yaitu @ovo_id dan @gopayindonesia dengan menggunkan Twitter
API (Application Programming Interface). Hasil analisis
sentiment menunjukkan sebagian besar ulasan masyarakat tentang
dompet digital yang diunggah di Twitter mengandung sentimen
positif dan presentase ulasan negatif pada dompet digital Gopay
lebih kecil dibandingkan dompet digital OVO. Selanjutnya
dilakukan analisis klasifikasi menggunakan metode Support
Vector Machine (SVM) dan Convolutional Neural Network (CNN).
Metode klasifikasi yang sesuai adalah SVM Kernel RBF dengan
rata-rata nilai accuracy 0,982 untuk dompet digital OVO dan
0,947 untuk dompet digital Gopay. Metode klasifikasi CNN
memiliki nilai accuracy yang lebih kecil yaitu 0,884 untuk dompet
digital OVO dan 0,689 untuk Gopay.
====================================================================================================
The digital wallet application is a new payment method that
is trending in Indonesia. There are many digital wallet
applications in the community with their respective superior
features. Public assessment of digital wallet services can be
obtained through social media. This study was conducted to
determine the public's response to digital wallet services based on
public sentiment using crawled data from two keywords, namely
@ovo_id and @gopayindonesia using the Twitter API (Application
Programming Interface). The results of the sentiment analysis
show that most of the public reviews about digital wallets uploaded
on Twitter contain positive sentiments and the percentage of
negative reviews on the Gopay digital wallet is smaller than the
OVO digital wallet. Furthermore, classification analysis was
carried out using the Support Vector Machine (SVM) and
Convolutional Neural Network (CNN) methods. The appropriate
classification method is SVM Kernel RBF with an average
accuracy value of 0,982 for the OVO digital wallet and 0,947 for
the Gopay digital wallet. The CNN classification method has a
smaller accuracy value, namely 0,884 for the OVO digital wallet
and 0,689 for Gopay.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Convolution Neural network, Digital Wallet, Support Vector Machine, Twitter, Convolution Neural network, Dompet Digital, Support Vector Machine, Twitter.
Subjects:	H Social Sciences > HA Statistics H Social Sciences > HA Statistics > HA29 Theory and method of social science statistics
Divisions:	Faculty of Mathematics and Science > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Ardiansyah Setyo
Date Deposited:	10 Sep 2021 04:06
Last Modified:	10 Sep 2021 04:06
URI:	http://repository.its.ac.id/id/eprint/91950

Actions (login required)

View Item