Nuraisma, Faza Fakhrian (2022) Analisis Sentimen Pengguna Aplikasi Flip Dan OY! indonesia Dengan Metode Naive Bayes Classifier. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 10611710000091-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
10611710000091-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2024. Download (1MB) | Request a copy |
|
Text
10611710000091-Undergraduate_Thesis.pdf Restricted to Registered users only Download (1MB) | Request a copy |
Abstract
Perusahaan startup saat ini yang berbasis aplikasi dalam memenuhi kebutuhan transaksi keuangan hingga kebutuhan finansial adalah perusahaan Flip dan OY! Indonesia. Kedua perusahaan ini tentunya memiliki opini dari pengguna aplikasi berupa komentar yang bisa dijadikan evaluasi dalam melakukan pengembangan untuk aplikasi kedepannya. Selama ini perusahaan melakukan analisis opini pengguna secara manual, karena jumlah opini yang dianalisis banyak, maka metode analisis manual membutuhkan waktu yang lama. Oleh karena
itu, diperlukan metode yang dapat menganalisis opini lebih cepat dan akurat yaitu analisis sentimen dengan metode Naïve Bayes Classifier(NBC). Hasil penelitian menunjukkan bahwa untuk analisis sentimen dengan kategori sentimen yang paling tertinggi pada aplikasi Flip adalah sentimen positif sebesar 60%, sedangkan pada aplikasi OY! Indonesia adalah sentimen negatif sebesar 53%. Dengan metode NBC dapat dikatakan bahwa aplikasi Flip memiliki hasil ketepatan klasifikasi terbaik dengan nilai accuracy sebesar 67,92%, nilai sensitivity
sebesar 65,62%, dan nilai specificity sebesar 71,43%.
=====================================================================================================
Today's startup companies that are application-based in
meeting financial transaction needs to financial needs are Flip and OY! Indonesian. Both companies certainly have opinions from application users in the form of comments that can be used as an evaluation in developing for future applications. During this time the company conducts user opinion analysis manually, because the number of opinions analyzed is many, then manual analysis methods take a long time. Therefore, a method that can analyze opinions
more quickly and accurately is sentiment analysis with the Naïve Bayes Classifier (NBC) method. The results showed that for sentiment analysis with the highest sentiment category on the Flip application was positive sentiment by 60%, while on the OY! Indonesian app is a negative sentiment of 53%. With the NBC method it can be said that the Flip application has the best classification accuracy results with an accuracy value of 67.92%, a sensitivity value of 65.62%, and a specificity value of 71.43%.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Sentiment analysis, Application, Flip, Naïve Bayes Classifier, Opinions, OY! Indonesian, Analisis Sentimen, Aplikasi, Flip, Naïve Bayes Classifier, Opini, OY! Indonesia. |
| Subjects: | H Social Sciences > HA Statistics H Social Sciences > HA Statistics > HA29 Theory and method of social science statistics Q Science > QA Mathematics > QA279.5 Bayesian statistical decision theory. |
| Divisions: | Faculty of Vocational > 49501-Business Statistics |
| Depositing User: | FAZA FAKHRIAN NURAISMA |
| Date Deposited: | 04 Mar 2022 02:06 |
| Last Modified: | 01 Nov 2022 03:51 |
| URI: | http://repository.its.ac.id/id/eprint/94776 |
Actions (login required)
 |
View Item |