KURNIAWAN, FREDI (2021) ANALISA OPINI ULASAN PRODUK TOKO ONLINE ATRIA FURNITURE PADA MARKETPLACE TOKOPEDIA INDONESIA MENGUNAKAN METODE SUPPORT VECTOR MACHINE DAN MAXIMUM ENTROPY. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 Cover.pdf Download (1MB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
02 Bab 1.pdf Restricted to Registered users only Download (89kB) |
|
|
Text (BAB II)
03 Bab 2.pdf Restricted to Registered users only Download (163kB) |
|
|
Text (BAB III)
04 Bab 3.pdf Restricted to Registered users only Download (99kB) |
|
|
Text (BAB IV)
05 Bab 4.pdf Restricted to Registered users only Download (97kB) |
|
|
Text (BAB V)
06 Bab 5.pdf Restricted to Registered users only Download (966kB) |
|
|
Text (BAB VI)
07 Bab 6.pdf Restricted to Registered users only Download (86kB) |
|
|
Text (DAFTAR PUSTAKA)
08 Daftar Pustaka.pdf Restricted to Registered users only Download (83kB) |
|
|
Text (LAMPIRAN)
09 Lampiran.pdf Restricted to Registered users only Download (292kB) |
Abstract
Product reviews in the marketplace are valuable information if processed properly. Sellers can analyze product reviews to get information that can be used in evaluating products and services. Analysis of product reviews is not enough just by looking at the number of stars, it is necessary to look at the entire contents of review comments to get information from reviews. However, for a large number of reviews analysis, a special method or technique is needed that is able to analyze many reviews, whether it means positive or negative. The method used is Support Vector Machine and Maximum Entropy to classify product review data on the "Atria Furniture" Online Store in the Tokopedia marketplace. The sentiment analysis stages consist of data collection, the data cleansing process or the preprocessing stage for the application of the related algorithm, and displaying the results in the form of data visaification. Based on the test results, the SVM classification method obtained an accuracy rate of 98.74%. Meanwhile, the Maxent method provides a higher level of accuracy, which is 99.96%. Key words: Analisa opini, sentiment analysis, Support Vector Machine, Maximum Entropy, computer science, mercu buana university Ulasan produk di marketplace merupakan informasi yang berharga apabila diolah dengan baik. Penjual dapat melakukan analisis ulasan produk untuk mendapatkan informasi yang dapat digunakan dalam melakukan evaluasi produk dan layanan. Analisis ulasan produk tidak cukup hanya dengan melihat dari jumlah bintang, diperlukan melihat seluruh isi komentar ulasan untuk mendapat informasi dari ulasan. Akan tetapi untuk Analisi ulasan dalam jumlah yang banyak itu, diperlukan sebuah metode atau Teknik khusus yang mampu menganalis banyak ulasan, apakah termaksud positif atau negatif. Metode yang digunakan Support Vector Machine dan Maximum Entropy untuk mengklasifikasikan data ulasan produk pada Toko Online “Atria Furniture” di marketplace Tokopedia. Tahapan analisis sentimen terdiri dari pengumpulan data, proses pembersihan data (data cleansing) atau tahap preprocessing proses penerapan algoritma terkait, serta menampilkan hasil nya dalam bentuk visaulisasi data. Berdasarkan hasil pengujian, Klasifikasi dengan metode SVM diperoleh tingkat akurasi sebesar 98,74%. Sedangkan dengan metode Maxent memberikan tingkat akurasi yang lebih tinggi yaitu sebesar 99,96%. Kata Kunci : Analisa opini, sentiment analysis, Support Vector Machine, Maximum Entropy Ilmu Komputer, Universitas Mercu buana
Actions (login required)
 |
View Item |
