NAS, MUHAMMAD ILHAM (2024) ANALISIS SENTIMEN KEPUASAN PENGGUNA APLIKASI ACCESS BY KAI MENGGUNAKAN METODE SUPPORT VECTOR MACHINE DAN RANDOM FOREST. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01. Hal Cover.pdf Download (950kB) | Preview |
|
|
Text (ABSTRAK)
02. Abstrak.pdf Download (114kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
03. BAB I.pdf Restricted to Registered users only Download (149kB) |
|
|
Text (BAB II)
04. BAB II.pdf Restricted to Registered users only Download (402kB) |
|
|
Text (BAB III)
05. BAB III.pdf Restricted to Registered users only Download (357kB) |
|
|
Text (BAB IV)
06. BAB IV.pdf Restricted to Registered users only Download (1MB) |
|
|
Text (BAB V)
07. BAB V.pdf Restricted to Registered users only Download (81kB) |
|
|
Text (DAFTAR PUSTAKA)
08. Daftar Pustaka.pdf Restricted to Registered users only Download (125kB) |
|
|
Text (LAMPIRAN)
09. Lampiran.pdf Restricted to Registered users only Download (534kB) |
Abstract
The app "Acces by KAI" has diverse opinions in the review column which is a problem in performance evaluation because there is no systematic way to classify reviews as positive, neutral, or negative. This research proposes the use of sentiment analysis to classify user reviews of the app. This research uses data on the application's review column using the Support Vector Machine and Random Forest methods. Another goal of this research is to compare the performance of the two algorithms. The test results using SVM show an accuracy rate of 82% while Random Forest is higher producing an accuracy of 84%, it can be concluded that the performance of the Random Forest model is better and more efficient for classifying sentiment data. The visualisation results show that the majority of Access by KAI application users are not satisfied, as evidenced by the data of 5771 negative reviews, 735 positive reviews and 469 neutral reviews. This information can be used by companies to improve services and increase user satisfaction. Keywords: Sentiment Analysis, Acces by KAI, Support Vector Machine, Random Forest Aplikasi "Acces by KAI" memiliki beragam opini dalam kolom ulasan menjadi masalah dalam evaluasi kinerja karena tidak ada cara sistematis untuk mengklasifikasikan ulasan sebagai positif, netral, atau negatif. Penelitian ini mengusulkan penggunaan analisis sentimen untuk mengklasifikasikan ulasan pengguna terhadap aplikasi tersebut. Penelitian ini menggunakan data pada kolom ulasan aplikasi tersebut menggunakan metode Support Vector Machine dan Random Forest. Tujuan lain penelitian ini yaitu untuk membandingkan kinerja kedua algoritma tersebut. Hasil pengujian menggunakan SVM menunjukkan tingkat akurasi sebesar 82% sedangkan Random Forest lebih tinggi menghasilkan akurasi 84%, dapat disimpulkan bahwa kinerja model Random Forest lebih baik dan efisien untuk mengklasifikasikan data sentimen. Hasil visualisasi menunjukan bahwa mayoritas pengguna aplikasi “Access by KAI” tidak puas, terbukti dengan data 5771 ulasan negatif, 735 ulasan positif dan 469 ulasan netral. Informasi ini dapat digunakan perusahaan untuk memperbaiki layanan dan meningkatkan kepuasan pengguna. Kata kunci: Analisis Sentimen, Acces by KAI, Support Vector Machine, Random Forest
| Item Type: | Thesis (S1) |
|---|---|
| Call Number CD: | FIK/SI. 24 094 |
| Call Number: | SIK/18/24/045 |
| NIM/NIDN Creators: | 41820010001 |
| Uncontrolled Keywords: | Analisis Sentimen, Acces by KAI, Support Vector Machine, Random Forest |
| Subjects: | 100 Philosophy and Psychology/Filsafat dan Psikologi > 150 Psychology/Psikologi > 154 Subconscious and Altered States and Process/Psikologi Bawah Sadar > 154.6 Sleep Phenomena/Fenomena Tidur > 154.63 Dreams/Mimpi > 154.634 Analysis/Analisis 700 Arts/Seni, Seni Rupa, Kesenian > 710 Civic and Lanscape Art/Seni Perkotaan dan Pertamanan > 719 Natural Landscapes/Pertamanan Alam |
| Divisions: | Fakultas Ilmu Komputer > Sistem Informasi |
| Depositing User: | khalimah |
| Date Deposited: | 24 Jul 2024 07:56 |
| Last Modified: | 24 Jul 2024 07:56 |
| URI: | http://repository.mercubuana.ac.id/id/eprint/89811 |
Actions (login required)
 |
View Item |
