Irfan Muhammad Guvian, . (2024) IMPLEMENTASI ALGORITMA SUPPORT VECTOR MACHINE UNTUK KLASIFIKASI KALIMAT TERHADAP ULASAN APLIKASI TRAVELIO PADA GOOGLE PLAY STORE. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (114kB) |
|
Text
AWAL.pdf Download (561kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (204kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (485kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (738kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (940kB) |
|
Text
BAB 5.pdf Download (172kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (176kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (62kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (3MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (1MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (427kB) |
Abstract
This research has a background, namely that there is a difference between the reviews given by Android application users and the ratings given. Therefore, this research aims to build a sentence classification model that can classify the sentiment of user reviews of the Travelio application on the Google Play Store page into 3 sentiment classes, positive, negative, and neutral using the Support Vector Machine algorithm. Apart from that, this research was conducted to find out the results of evaluating the classification of models that have been built using the confusion matrix and to compare the classification results with the ratings. The steps taken to build the model include data collection, data preprocessing, automatic labeling using the VADER algorithm, word weighting using TF-IDF, and hyperparameterization using Grid Search with parameters Cost (C) 1,10,100 and gamma 0.1 to 1. In this research, A comparison of three compositions was carried out, namely 70:30, 80:20, and 90:10 to find out the best composition based on the balance of the model in carrying out classification which is shown in the confusion matrix results which are symbolized by the magnitude of the F1-Score. The classification results based on the confusion matrix show that the best composition was obtained using a 70:30 composition with an accuracy value of 89.8%, precision of 82%, recall of 70%, and F1-Score 74%. This research also found based on the classification results that the rating cannot be used as a parameter for customer satisfaction because it still contains inappropriate sentiments.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2010511084] [Pembimbing 1: Neny Rosmawarni] [Pembimbing 2: Muhammad Panji Muslim] [Penguji 1: Nur Hafifah Matondang] [Penguji 2: Theresia Wati] |
| Uncontrolled Keywords: | Support Vector Machine, Travelio, VADER, confusion matrix |
| Subjects: | Q Science > QA Mathematics > QA76 Computer software T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | IRFAN MUHAMMAD GUVIAN |
| Date Deposited: | 30 Jul 2024 05:30 |
| Last Modified: | 09 Sep 2024 01:36 |
| URI: | http://repository.upnvj.ac.id/id/eprint/30718 |
Actions (login required)
 |
View Item |