Tarisa Citra Dewi, - (2023) ANALISIS SENTIMEN TWEET OPINI MASYARAKAT TERHADAP KEPUASAN KEKUATAN SINYAL DAN KECEPATAN INTERNET PROVIDER INDOSAT OOREDOO HUTCHISON SAAT PANDEMI COVID-19. S1 thesis, Universitas Pendidikan Indonesia.
![[img]](http://repository.upi.edu/style/images/fileicons/text.png) |
Text
S_SISTEL_1904301_Title.pdf Download (817kB) |
|
Text
S_SISTEL_1904301_Chapter1.pdf Download (456kB) |
|
Text
S_SISTEL_1904301_Chapter2.pdf Restricted to Staf Perpustakaan Download (884kB) |
|
Text
S_SISTEL_1904301_Chapter3.pdf Download (414kB) |
|
Text
S_SISTEL_1904301_Chapter4.pdf Restricted to Staf Perpustakaan Download (963kB) |
|
Text
S_SISTEL_1904301_Chapter5.pdf Download (250kB) |
|
Text
S_SISTEL_1904301_Appendix.pdf Restricted to Staf Perpustakaan Download (719kB) |
Abstract
Proses analisis sentimen merupakan proses mengolah atau menganalisis data yang berupa opini, emosi, evaluasi, dan sikap seseorang terhadap barang, orang, ataupun peristiwa. Pada sebuah perusahaan, analisis sentimen sangat penting dilakukan guna mengetahui pandangan masyarakat terhadap suatu produk ataupun layanan, melalui umpan balik dari masyarakat sehingga dapat dijadikan bahan kajian indikator peningkatan dari produk atau layanan itu sendiri. Penelitian ini menggunakan metode algoritma Naïve Bayes dan tool Rapidminer untuk melakukan pemrosesan data. Tujuan dari penelitian ini untuk mengetahui bagaimana persentase sentimen negatif dan sentimen positif tentang opini masyarakat berdasarkan tweet terhadap kepuasan kekuatan sinyal dan kecepatan internet provider Indosat Ooredoo Hutchison saat pandemi Covid-19 pada media sosial Twitter. Penelitian ini menggunakan 10.000 data Twitter. Hasil dari penelitian ini yaitu 45% sentimen masyarakat bernilai negatif dan 55% sentimen bernilai positif dengan tingkat akurasi sebesar 72,85% dengan recall pada sentimen positif bernilai 79,09%, recall pada sentimen negatif 66,60% dan precision pada prediksi positif 70,31%, precision pada prediksi negatif bernilai 76.11%. ----- Sentiment analysis is the process of processing or analyzing data consisting of opinions, emotions, evaluations, and attitudes of individuals towards products, people, or events. In a company, sentiment analysis is crucial to understand the public's perception of a product or service through feedback, enabling it to serve as a basis for improving the said product or service. This research employs the Naïve Bayes algorithm and the Rapidminer tool for data processing. The aim of this study is to determine the percentage of negative and positive sentiments in public opinions based on tweets regarding the satisfaction with the signal strength and internet speed of the Indosat Ooredoo Hutchison provider during the Covid-19 pandemic on the Twitter social media platform. This study involves 10,000 Twitter data entries. The results of this research indicate that 45% of public sentiments are negative, while 55% are positive. The accuracy rate achieved is 72.85%, with a recall rate of 79.09% for positive sentiments, a recall rate of 66.60% for negative sentiments, a precision rate of 70.31% for positive predictions, and a precision rate of 76.11% for negative predictions.
| Item Type: | Thesis (S1) |
|---|---|
| Additional Information: | Hafiyyan Putra Pratama : ID SINTA : 6681148 Link Google Scholar : https://scholar.google.com/citations?hl=id&user=tQe1410AAAAJ Ahmad Fauzi : ID SINTA : 6122861 Linnk Google Scholar : https://scholar.google.com/citations?hl=id&user=b6BGJbEAAAAJ |
| Uncontrolled Keywords: | Analisis Sentimen, Naïve Bayes, RapidMiner |
| Subjects: | L Education > L Education (General) T Technology > T Technology (General) |
| Divisions: | UPI Kampus Purwakarta > S1 Sistem Telekomunikasi |
| Depositing User: | Tarisa Citra Dewi |
| Date Deposited: | 04 Sep 2023 03:32 |
| Last Modified: | 04 Sep 2023 04:12 |
| URI: | http://repository.upi.edu/id/eprint/100556 |
Actions (login required)
 |
View Item |