Analisis Kualitas Aplikasi Vidio Berbasis Ulasan Pengguna dengan Menggunakan Text Mining, Kano Model, dan Quality Function Deployment

Lauren, Lukas (2025) Analisis Kualitas Aplikasi Vidio Berbasis Ulasan Pengguna dengan Menggunakan Text Mining, Kano Model, dan Quality Function Deployment. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5010211095-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (2MB) | Request a copy

Abstract

Vidio sebagai salah satu platform layanan Over-The-Top (OTT) terkemuka di Indonesia, terus mencatatkan pertumbuhan pengguna yang signifikan dari tahun ke tahun. Namun, popularitas ini diiringi dengan tingginya jumlah keluhan yang tercermin dari ulasan pengguna di Google Play Store, yang mengindikasikan adanya kesenjangan antara harapan pengguna dan kualitas layanan yang diberikan. Penelitian ini bertujuan untuk menjembatani kesenjangan tersebut melalui perancangan strategi peningkatan kualitas layanan berbasis analisis data. Sebanyak 20.000 ulasan terbaru diekstraksi dan dianalisis secara komprehensif menggunakan pendekatan terintegrasi yang terdiri dari Text Mining, K-Means Clustering, Model Kano, dan Quality Function Deployment (QFD). Analisis awal menggunakan K-Means Clustering menghasilkan delapan klaster dominan yang merepresentasikan permasalahan teknis seperti buffering saat siaran langsung, iklan yang mengganggu, kendala aktivasi langganan, serta ketidaksesuaian sistem billing. Berdasarkan analisis Model Kano, sepuluh atribut kebutuhan pelanggan dikategorikan ke dalam tiga kelompok, yaitu must-be (waktu akses konten yang cepat, sinkronisasi pembayaran, sistem billing yang akurat), one-dimensional (performa streaming stabil, aktivasi layanan otomatis, proses langganan bebas error, pengurangan frekuensi iklan, penempatan iklan yang tidak mengganggu), dan attractive (kinerja aplikasi yang ringan, desain UI/UX yang mudah dipahami). Tahap akhir menerjemahkan kebutuhan tersebut menjadi prioritas teknis melalui House of Quality (HoQ). Tiga prioritas utama yang harus segera diimplementasikan adalah integrasi sistem pembayaran (263,3), audit billing otomatis (235,1), serta pemantauan performa aplikasi secara real-time (193,0). Hasil penelitian ini memberikan kerangka kerja strategis untuk pengambilan keputusan teknis yang lebih efektif dan tepat sasaran dalam peningkatan kualitas layanan OTT.
=================================================================================================================================
Vidio, one of the leading Over-The-Top (OTT) service platforms in Indonesia, is experiencing significant year-over-year user growth. However, this popularity is accompanied by a high volume of complaints reflected in its Google Play Store reviews, indicating a gap between user expectations and the actual service quality. This research aims to bridge this gap by designing a data-driven strategy for service quality improvement. A total of 20,000 recent reviews were extracted and comprehensively analyzed using an integrated approach consisting of Text Mining, K-Means Clustering, the Kano Model, and Quality Function Deployment (QFD). Initial analysis using K-Means Clustering identified eight dominant clusters representing technical issues such as buffering during live broadcasts, intrusive advertisements, subscription activation issues, and billing system discrepancies. Through the Kano Model, ten key customer requirements were categorized into three groups: must-be (fast content access, payment synchronization, accurate billing), one-dimensional (stable streaming performance, automatic service activation, error-free subscription process, reduced ad frequency, unobtrusive ad placement), and attractive (lightweight application performance, easy-to-understand UI/UX design). The final stage translates these requirements into technical priorities using the House of Quality (HoQ). The top three priorities for immediate implementation are payment system integration (263.3), automated billing audits (235.1), and real-time application performance monitoring (193.0). This study provides a strategic framework for more effective and targeted technical decision-making to enhance OTT service quality.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Analisa Kualitas, Model Kano, Quality Function Deployment, Text Mining, Ulasan Pengguna, Quality Analysis, Kano Model, Quality Function Deployment, Text Mining, User Reviews
Subjects:	T Technology > TS Manufactures > TS156 Quality Control. QFD. Taguchi methods (Quality control)
Divisions:	Faculty of Industrial Technology and Systems Engineering (INDSYS) > Industrial Engineering > 26201-(S1) Undergraduate Thesis
Depositing User:	Lukas Lauren
Date Deposited:	21 Jul 2025 00:45
Last Modified:	21 Jul 2025 00:45
URI:	http://repository.its.ac.id/id/eprint/120105

Actions (login required)

View Item