Search for collections on EPrints Repository UNTIRTA

USULAN PERBAIKAN APLIKASI SIAKANG BERDASARKAN ANALISIS SENTIMEN MENGGUNAKAN PENDEKATAN QUALITY FUNCTION DEPLOYMENT (QFD)

Muhammad, Maulana Farid (2026) USULAN PERBAIKAN APLIKASI SIAKANG BERDASARKAN ANALISIS SENTIMEN MENGGUNAKAN PENDEKATAN QUALITY FUNCTION DEPLOYMENT (QFD). S1 thesis, Fakultas Teknik Universitas Sultan Ageng Tirtayasa.

[img] Text (SKRIPSI)
Maulana Farid Muhammad_3333210029_Fulltext.pdf
Restricted to Registered users only

Download (4MB)
[img] Text
Maulana Farid Muhammad_3333210029_01.pdf

Download (2MB)
[img] Text
Maulana Farid Muhammad_3333210029_02.pdf

Download (1MB)
[img] Text
Maulana Farid Muhammad_3333210029_03.pdf

Download (902kB)
[img] Text
Maulana Farid Muhammad_3333210029_04.pdf

Download (2MB)
[img] Text
Maulana Farid Muhammad_3333210029_05.pdf

Download (505kB)
[img] Text
Maulana Farid Muhammad_3333210029_06.pdf

Download (402kB)
[img] Text
Maulana Farid Muhammad_3333210029_Ref.pdf

Download (443kB)
[img] Text
Maulana Farid Muhammad_3333210029_Lamp.pdf

Download (853kB)
[img] Text
Maulana Farid Muhammad_3333210029_CP.pdf

Download (195kB)

Abstract

The implementation of the New Generation Academic Information System (SIAKANG) at Universitas Sultan Ageng Tirtayasa has faced various student complaints regarding service quality, with specific issues including technical difficulties in the login process, inaccuracies in academic grade data, slow loading times, frequent system errors, and a non-responsive user interface on mobile devices. This study aims to classify student opinions through sentiment analysis, identify key problem topics, and formulate structured service improvement recommendations based on user needs. The method employed is a quantitative approach with data collection via open-ended questionnaires (104 respondents), processed through text preprocessing stages, Term Frequency–Inverse Document Frequency (TF–IDF) numerical representation, and clustering using the K-Means algorithm. The determination of the optimal number of clusters via the Elbow Method resulted in k=3, with a Silhouette Score validation of 0.111, which was then integrated into the Quality Function Deployment (QFD) method through the construction of the House of Quality (HoQ) matrix. The study concludes that although the combination of TF-IDF and K-Means was not optimal in separating sentiment polarity due to data imbalance, the method was highly effective in mapping system weaknesses. The primary priorities for SIAKANG service improvement include strengthening system security, periodic academic data audits, server infrastructure optimization, and user interface/experience (UI/UX) enhancements to sustainably improve the quality of academic information services.

Item Type: Thesis (S1)
Contributors:
ContributionContributorsNIP/NIM
Thesis advisorBahauddin, Achmad19781221005011002
Additional Information: Implementasi Sistem Informasi Akademik New Generation (SIAKANG) di Universitas Sultan Ageng Tirtayasa menghadapi berbagai keluhan mahasiswa terkait kualitas layanan, dengan permasalahan spesifik berupa kendala teknis proses login, ketidaksesuaian data nilai akademik, lambatnya waktu pemuatan (loading), sistem yang sering error, serta tampilan antarmuka yang kurang responsif pada perangkat seluler. Penelitian ini bertujuan untuk mengelompokkan opini mahasiswa melalui analisis sentimen, mengidentifikasi topik permasalahan utama, serta menyusun usulan perbaikan layanan yang terstruktur berdasarkan kebutuhan pengguna. Metode yang digunakan adalah pendekatan kuantitatif dengan pengumpulan data melalui kuesioner terbuka (104 responden), yang diolah melalui tahap text preprocessing, representasi numerik Term Frequency–Inverse Document Frequency (TF–IDF), dan pengelompokan menggunakan algoritma K Means Clustering. Penentuan jumlah klaster optimal melalui Elbow Method menghasilkan k=3, dengan validasi Silhouette Score sebesar 0,111, yang kemudian diintegrasikan ke dalam metode Quality Function Deployment (QFD) melalui penyusunan matriks House of Quality (HoQ). Penelitian menyimpulkan bahwa meskipun kombinasi TF-IDF dan K-Means belum optimal dalam memisahkan polaritas sentimen karena ketidakseimbangan data, metode ini sangat efektif memetakan titik lemah sistem, di mana prioritas utama perbaikan layanan SIAKANG meliputi penguatan keamanan sistem, audit data akademik berkala, optimasi infrastruktur server, dan peningkatan desain antarmuka pengguna (UI/UX) demi meningkatkan kualitas layanan secara berkelanjutan.
Subjects: H Social Sciences > H Social Sciences (General)
H Social Sciences > HA Statistics
Divisions: 03-Fakultas Teknik
03-Fakultas Teknik > 26201-Jurusan Teknik Industri
Depositing User: Maulana Farid Muhammad
Date Deposited: 08 Apr 2026 08:10
Last Modified: 08 Apr 2026 08:10
URI: http://eprints.untirta.ac.id/id/eprint/59504

Actions (login required)

View Item View Item