PUTRA, RIGA NORMANDA (2026) ANALISIS KEPUASAN PENGGUNA SISTEM ARROW DI LINGKUNGAN KEMENTERIAN PEKERJAAN UMUM MENGGUNAKAN METODE DATA MINING DENGAN ALGORITMA SUPPORT VECTOR MACHINE (SVM). S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
Cover.pdf Download (610kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
Bab 1.pdf Restricted to Registered users only Download (43kB) |
|
|
Text (BAB II)
Bab 2.pdf Restricted to Registered users only Download (96kB) |
|
|
Text (BAB III)
Bab 3.pdf Restricted to Registered users only Download (43kB) |
|
|
Text (BAB IV)
Bab 4.pdf Restricted to Registered users only Download (72kB) |
|
|
Text (BAB V)
Bab 5.pdf Restricted to Registered users only Download (37kB) |
|
|
Text (DAFTAR PUSTAKA)
Daftar Pusaka.pdf Restricted to Registered users only Download (36kB) |
|
|
Text (LAMPIRAN)
Lampiran.pdf Restricted to Registered users only Download (864kB) |
Abstract
This study aims to analyze user satisfaction levels with the ARROW (Automated RFID Roadway) System at the Ministry of Public Works using a text mining approach. The research data was obtained from 250 active users of the ARROW System thru essay-form questionnaires. The stages of data processing include document formation, text preprocessing (case folding, tokenizing, stopword removal, and stemming), as well as word weighting using the Term Frequency– Inverse Document Frequency (TF-IDF) method. Satisfaction labels were formed using a rule-based approach, resulting in four categories: Fairly Satisfied, Satisfied, Very Satisfied, and Unsatisfied. Classification was then performed using the Support Vector Machine (SVM) algorithm with several training and testing data split scenarios (60:40, 70:30, 80:20, and 90:10). The results of the four-class classification tests showed stable accuracy in the range of 68%–70%, with the best result at the 80:20 split being 70%. Additionally, further testing was conducted by simplifying the labels into two classes (Satisfaction and Dissatisfaction) to compare the model's performance, which resulted in higher accuracy in the range of 88%– 89%, but was affected by the imbalance in data distribution. The results of this study indicate that the TF-IDF and SVM methods can be used to provide an overview of user satisfaction levels with the ARROW System and can serve as a basis for evaluation in future system development. Kata kunci: User Satisfaction, ARROW System, Text Mining, TF-IDF, Support Vector Machine Penelitian ini bertujuan untuk menganalisis tingkat kepuasan pengguna terhadap Sistem ARROW (Automated RFID Roadway) di lingkungan Kementerian Pekerjaan Umum menggunakan pendekatan text mining. Data penelitian diperoleh dari 250 responden pengguna aktif Sistem ARROW melalui kuesioner berbentuk esai. Tahapan pengolahan data meliputi pembentukan dokumen, preprocessing teks (case folding, tokenizing, stopword removal, dan stemming), serta pembobotan kata menggunakan metode Term Frequency–Inverse Document Frequency (TFIDF). Label kepuasan dibentuk menggunakan pendekatan rule-based sehingga menghasilkan empat kategori yaitu Cukup Puas, Puas, Sangat Puas, dan Tidak Puas, kemudian dilakukan klasifikasi menggunakan algoritma Support Vector Machine (SVM) dengan beberapa skenario pembagian data latih dan data uji (60:40, 70:30, 80:20, dan 90:10). Hasil pengujian pada klasifikasi empat kelas menunjukkan akurasi yang stabil pada rentang 68%–70%, dengan hasil terbaik pada split 80:20 sebesar 70%. Selain itu, dilakukan pengujian tambahan dengan penyederhanaan label menjadi dua kelas (Puas dan Tidak Puas) untuk membandingkan performa model, yang menghasilkan akurasi lebih tinggi pada rentang 88%–89%, namun dipengaruhi oleh ketidakseimbangan distribusi data. Hasil penelitian ini menunjukkan bahwa metode TF-IDF dan SVM dapat digunakan untuk memberikan gambaran umum tingkat kepuasan pengguna terhadap Sistem ARROW serta dapat menjadi bahan evaluasi dalam pengembangan sistem ke depannya. Kata kunci: Kepuasan Pengguna, Sistem ARROW, Text Mining, TF-IDF, Support Vector Machine.
Actions (login required)
 |
View Item |
