ANALISIS SENTIMEN PADA ULASAN PRODUK MASKER DI MARKETPLACE SHOPEE MENGGUNAKAN SUPPORT VECTOR MACHINE DAN SELEKSI FITUR CHI SQUARE

Willy Winata, . (2022) ANALISIS SENTIMEN PADA ULASAN PRODUK MASKER DI MARKETPLACE SHOPEE MENGGUNAKAN SUPPORT VECTOR MACHINE DAN SELEKSI FITUR CHI SQUARE. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (90kB)
[img] Text
AWAL.pdf
Download (453kB)
[img] Text
BAB 1.pdf
Download (106kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (254kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (192kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (810kB)
[img] Text
BAB 5.pdf
Download (107kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (147kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (97kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (352kB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (12MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (570kB)

Abstract

Masks are mandatory when you want to walk away from home, which makes mask sales increase drastically. However, with the limitation of these activities, conventional selling activities are hampered. Therefore, many people switch from direct shopping to online shopping. Shopee Marketplace is an online shopping platform. The sale of masks in the Shopee marketplace has experienced a very drastic increase which has made variations in the assessment of different product reviews from buyers. In this study, sentiment analysis is divided into 2 positive and negative classes based on the rating review. The classification algorithm used is a Support Vector Machine (SVM) with a Radial Basis Function (RBF) kernel and applies the Chi Square feature selection. The result of performance level using the Chi Square feature selection with a significance level value (α) of 0.3 obtained an accuracy of 91,32%, precision of 93,28%, recall of 93,14% and f1-score of 93,21%. Compared to the result of performance level without using feature selection, it only obtained an accuracy of 90.75%, precision of 92.08%, recall of 93.59% and f1-score of 92.83%.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 1810511095] [Pembimbing 1: Ati Zaidiah] [Pembimbing 2: Nurul Chamidah] [Penguji 1: Henki Bayu Seta] [Penguji 2: Mayanda Mega Santoni]
Uncontrolled Keywords: Mask, Sentiment Analysis, Marketplace, Shopee, Product Review, Support Vector Machine, Chi Square
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: Willy Winata
Date Deposited: 10 Aug 2022 03:10
Last Modified: 10 Aug 2022 03:10
URI: http://repository.upnvj.ac.id/id/eprint/19724

Actions (login required)

View Item View Item