Duma Sere Pakpahan, - (2024) ANALISIS SENTIMEN PENGGUNA APLIKASI GRAB BERDASARKAN ULASAN PENGGUNA DI GOOGLE PLAY STORE MENGGUNAKAN METODE ALGORITMA NAÏVE BAYES. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (6MB) |
|
Text
AWAL.pdf Download (6MB) |
|
Text
BAB I.pdf Download (6MB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (6MB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (6MB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (6MB) |
|
Text
BAB V.pdf Download (6MB) |
|
Text
DAFTAR PUSTAKA.pdf Download (6MB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (6MB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (6MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (395kB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (788kB) |
Abstract
The Grab app has become one of the leading platforms in the transportation and delivery service industry, offering ease of accessibility and a variety of services. It has become the top choice for many users in the region. However, in operating such a large platform, it is essential to continuously understand user views and sentiments towards the services provided. This research aims to conduct sentiment analysis on user reviews of the Grab app published on the Google Play Store using the Naïve Bayes Classifier algorithm to classify the reviews into positive and negative categories. The review data, collected from October 2023 to April 2024, was manually labeled by three annotators. The data processing went through several stages: preprocessing, word weighting using the Term Frequency – Inverse Document Frequency (TF-IDF) method, and data splitting. The research results show that the Naive Bayes classification model achieved fairly good accuracy, with an accuracy of 91%, precision of 81%, recall of 89%, and an F1-score of 85%, using a 90:10 training-to-test data ratio. In addition to the classification results, this research also created data visualization in the form of a Word Cloud to identify keywords that frequently appear in positive and negative reviews. Another output is a simple website that displays the classification results and visualizations based on the generated data. Through this analysis, the goal is to provide better insights into user perceptions of the Grab app and to understand which areas require improvement or enhancement of services.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2010512113] [Pembimbing 1: Tri Rahayu] [Pembimbing 2: Mohamad Bayu Wibisono] [Penguji 1: Nur Hafifah Matondang] [Penguji 2: Bambang Tri Wahyono] |
| Uncontrolled Keywords: | Sentiment Analysis, Naïve Bayes, Grab, Google Play Store |
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Sistem Informasi (S1) |
| Depositing User: | DUMA SERE PAKPAHAN |
| Date Deposited: | 13 Sep 2024 06:56 |
| Last Modified: | 13 Sep 2024 06:56 |
| URI: | http://repository.upnvj.ac.id/id/eprint/31605 |
Actions (login required)
 |
View Item |