CD Skripsi

Komparasi Fungsi Kernel Pada Algoritma Support Vector Machine Mengenai Ulasan Shopeepay Dan Shopee Paylater

---

ABSTRACT
Internet users in Indonesia have reached 210 million people in December 2022. One of the activities of internet users is shopping through Shopee e-commerce which provides ShopeePay and Shopee PayLater payment features. In improving these features, it is important for Shopee to know user reviews as an evaluation to improve the quality that can be seen on the Google Play Store. This study aims to classify positive and negative reviews using Support Vector Machine (SVM) with several kernel functions, such as linear, polynomial, Radial Basis Function (RBF), and sigmoid kernel. The results of sentiment analysis are visualized with a word cloud and then viewed the text associations of each sentiment class. The best classification results in ShopeePay and Shopee PayLater reviews are given by polynomial kernels with levels of accuracy, sensitivity, and specificity respectively in reviews of 88.64%, 57.47%, 98.70%, and 86.71%, 56.49%, 99.14%. Text associations in the positive sentiment class of ShopeePay reviews include vouchers, freebies, shipping, while negative sentiments related to admin fees. Shopee PayLater users in positive sentiment talk about free shipping vouchers, while negative sentiments talk about late fines for paying bills.
Keywords : Shopeepay, shopee paylater, reviews, Support Vector Machine (SVM), kernel functions

---

Ketersediaan

Informasi Detail

Judul Seri

-

No. Panggil

1903113940

Penerbit

Pekanbaru : Universitas Riau – FMIPA – STATISTIKA., 2023

Deskripsi Fisik

-

Bahasa

Indonesia

ISBN/ISSN

-

Klasifikasi

1903113940

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

STATISTIKA

Info Detail Spesifik

-

Pernyataan Tanggungjawab

PUJA

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar