Analisis Sentimen Aplikasi Shopee Pada Google Play Store Menggunakan Naive Bayes & CART

AFANDI, YUYUS (2023) Analisis Sentimen Aplikasi Shopee Pada Google Play Store Menggunakan Naive Bayes & CART. S1 thesis, Universitas Mercu Buana Bekasi.

Preview	Text 41519210013-Yuyus Afandi-01 Cover.pdf Download (854kB) | Preview
Preview	Text 41519210013-Yuyus Afandi-02 Abstrak.pdf Download (424kB) | Preview
	Text 41519210013-Yuyus Afandi-03 BAB 1.pdf Restricted to Registered users only Download (30kB)
	Text 41519210013-Yuyus Afandi-04 BAB 2.pdf Restricted to Registered users only Download (238kB)
	Text 41519210013-Yuyus Afandi-05 BAB 3.pdf Restricted to Registered users only Download (216kB)
	Text 41519210013-Yuyus Afandi-06 BAB 4.pdf Restricted to Registered users only Download (450kB)
	Text 41519210013-Yuyus Afandi-07 BAB 5.pdf Restricted to Registered users only Download (60kB)
	Text 41519210013-Yuyus Afandi-08 Daftar Pustaka.pdf Restricted to Registered users only Download (120kB)
	Text 41519210013-Yuyus Afandi-09 Lampiran.pdf Restricted to Registered users only Download (935kB)

Abstract

Penggunaan marketplace pada saat ini sangat membludak hingga menimbulkan persaingan pada banyaknya marketplace. Salah satu marketplace yang terkena dampak persaingan tersebut ialah Shopee. Data yang digunakan berjumlah 2648 data komentar. Penelitian ini menggunakan dua metode yaitu Algoritma Naive Bayes dan CART. Tujuan penelitian ini Untuk mengetahui hasil akurasi terbaik. Hasil penelitian menunjukan bahwa hasil testing report menggunakan Algoritma CART mendapatkan hasil akurasi atau f1-score sebesar 76%, presisi false negative 81%, presisi true positive 63%, recall negative 85% dan recall positive 56%. Dan hasil testing report menggunakan Algoritma Naïve Bayes mendapatkan hasil akurasi atau f1-score sebesar 82%, presisi false negative 86%, presisi true positive 75%, recall negative 90% dan recall positive 67%. Algoritma Naive Bayes memberikan performa yang lebih baik dibandingkan dengan Algoritma CART dalam menganalisis sentiment terhadap aplikasi Shopee di Google PlayStore dengan perbandingan akurasi berturut – turut sebesar 82%:76% Kata Kunci : Analisis Sentimen, Shopee, Naive Bayes, CART, Google PlayStore. The use of the marketplace at this time is so booming that it creates competition in the many marketplaces. One of the marketplaces affected by this competition is Shopee. The data used amounted to 2648 data comments. This study uses two methods, namely the Naive Bayes Algorithm and CART. The purpose of this study is to find out the best accuracy results. The results showed that the results of testing reports using the CART algorithm obtained an accuracy or f1-score of 76%, 81% false negative precision, 63% true positive precision, 85% negative recall and 56% positive recall. And the results of the testing report using the Naïve Bayes Algorithm get an accuracy or f1-score of 82%, 86% false negative precision, 75% true positive precision, 90% negative recall and 67% positive recall. The Naive Bayes Algorithm provides better performance compared to the CART Algorithm in analyzing sentiment towards the Shopee application on the Google PlayStore with a successive comparison of accuracy of 82%:76%. Keywords: Sentiment Analysis, Shopee, Naïve Bayes, CART, Google PlayStore

Actions (login required)

View Item